Proceedings of the 2018 Conference of the North

Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods (N18-2)

Challenge:	a study of coreference resolution systems that resolve gender differences in pairs is aimed at examining implicit gender biases.
Approach:	They propose a Winograd schema-style set of minimal pair sentences that differ only by gender . they evaluate and confirm systematic gender bias in three publicly-available coreference resolution systems .
Outcome:	The proposed system resolves a male and neutral pronoun as coreferent with "The surgeon" but does not resolve the female pronounce.

Copied to clipboard

Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, Kai-Wei Chang

Integrating Stance Detection and Fact Checking in a Unified Corpus (N18-2)

Challenge:	Existing methods for co-reference resolution focus on gender bias.
Approach:	They propose a new benchmark for co-reference resolution focused on gender bias, WinoBias.
Outcome:	The proposed system removes the bias without significantly affecting performance on existing datasets.

Copied to clipboard

Ramy Baly, Mitra Mohtarami, James Glass, Lluís Màrquez, Alessandro Moschitti, Preslav Nakov

Is Something Better than Nothing? Automatically Predicting Stance-based Arguments Using Deep Learning and Small Labelled Dataset (N18-2)

Challenge:	Existing methods for fact checking are not supported by existing datasets, which treat fact checking, document retrieval, source credibility, stance detection and rationale extraction as independent tasks.
Approach:	They propose to implement automatic fact checking on an Arabic fact checking corpus, which is the first of its kind.
Outcome:	The proposed approach is based on an Arabic fact checking corpus, the first of its kind.

Copied to clipboard

Pavithra Rajendran, Danushka Bollegala, Simon Parsons

Text Classification

Challenge:	Argument mining is a subset of NLP that deals with extracting arguments from user-based content.
Approach:	They propose to use weakly supervised and semi-supervised methods to automatically annotate reviews and provide large annotated datasets.
Outcome:	The proposed methods can be used to learn better models for implicit/explicit opinion classification.

Multi-Task Learning for Argumentation Mining in Low-Resource Settings (N18-2)

Copied to clipboard

Claudia Schulz, Steffen Eger, Johannes Daxenberger, Tobias Kahse, Iryna Gurevych

Low-Resource NLP

Challenge:	Argument component identification is difficult for trained annotators to perform in a new domain or to develop new AM tasks.
Approach:	They investigate whether multi-task learning can improve performance on AM problems . they found that MTL performs particularly well when little training data is available for the main task .
Outcome:	The proposed approach performs better when little training data is available for the main task, a common scenario in AM.

Neural Models for Reasoning over Multiple Mentions Using Coreference (N18-2)

Copied to clipboard

Bhuwan Dhingra, Qiao Jin, Zhilin Yang, William Cohen, Ruslan Salakhutdinov

Automatic Dialogue Generation with Expressed Emotions (N18-2)

Challenge:	Existing Recurrent Neural Network (RNN) layers are biased towards short-term dependencies and hence not suited to such tasks.
Approach:	They propose a recurrent layer which is instead biased towards coreferent dependencies and uses coreference annotations extracted from an external system to connect entity mentions belonging to the same cluster.
Outcome:	The proposed layer improves performance on Wikihop, LAMBADA and the bAbi AI datasets with large gains when training data is scarce.

Copied to clipboard

Chenyang Huang, Osmar Zaïane, Amine Trabelsi, Nouha Dziri

Dialogue Systems & Conversational Agents

Challenge:	a growing interest in neural dialogue generation systems is focusing on generating human-like responses based on past utterances . despite efforts, few consider putting restrictions on the response itself . authors present three models that concatenate the desired emotion with the source input .
Approach:	They propose three models that concatenate the desired emotion with the source input or push the emotion in the decoder.
Outcome:	The proposed model is more efficient than the previous models, but it lacks the emotion vector.

Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network (N18-2)

Copied to clipboard

Chenliang Li, Weiran Xu, Si Li, Sheng Gao

Natural Language Generation by Hierarchical Decoding with Linguistic Patterns (N18-2)

Challenge:	Abstractive text summarization models are hard to be controlled in the process of generation, which leads to a lack of key information.
Approach:	They propose a guiding generation model that combines extractive and abstractive methods to generate text summarization.
Outcome:	The proposed model improves on the CNN/Daily Mail dataset.

Copied to clipboard

Shang-Yu Su, Kai-Ling Lo, Yi-Ting Yeh, Yun-Nung Chen

Language Models

Challenge:	a common and mostly adopted method is the rule-based (or template-based) method for natural language generation.
Approach:	They propose a hierarchical decoding NLG model based on linguistic patterns in different levels.
Outcome:	The proposed method outperforms the traditional one with a smaller model size.

Neural Poetry Translation (N18-2)

Copied to clipboard

Marjan Ghazvininejad, Yejin Choi, Kevin Knight

RankME: Reliable Human Ratings for Natural Language Generation (N18-2)

Challenge:	despite recent advances in machine translation, automatic poetry translation remains a challenging problem.
Approach:	They propose a system that automatically translates a source text to an English poem . human evaluation of the translations ranks the quality as acceptable 78.2% of the time.
Outcome:	The proposed system always translates a source text to an English poem. human evaluation of the translations ranks the quality as acceptable 78.2% of the time.

Copied to clipboard

Jekaterina Novikova, Ondřej Dušek, Verena Rieser

Sentence Simplification with Memory-Augmented Neural Networks (N18-2)

Challenge:	Existing studies have shown that human evaluation for natural language generation often suffers from inconsistent user ratings.
Approach:	They propose a rank-based magnitude estimation method which combines continuous scales and relative assessments to improve the reliability of human ratings.
Outcome:	The proposed method significantly improves the reliability and consistency of human ratings compared to traditional evaluation methods.

Copied to clipboard

Tu Vu, Baotian Hu, Tsendsuren Munkhdalai, Hong Yu

A Corpus of Non-Native Written English Annotated for Metaphor (N18-2)

Challenge:	Sentence simplification aims to simplify the content and structure of complex sentences . prior work has focused on monolingual machine translation (MT) and tree-based MT (TBMT).
Approach:	They adapt an architecture with augmented memory capacities called Neural Semantic Encoders for sentence simplification.
Outcome:	The proposed architecture improves on different datasets and improves human judgments.

Copied to clipboard

Beata Beigman Klebanov, Chee Wee (Ben) Leong, Michael Flor

Challenge:	Using argumentation-relevant metaphor predicts a holistic score of essay quality, we show .
Approach:	They present a corpus of argumentative essays annotated for metaphor by non-native speakers of English . they also examine the relationship between writing proficiency and metaphor use .
Outcome:	The proposed corpus is made publicly available and evaluated . it shows that metaphor is a significant predictor of a holistic score of essay quality .

A Simple and Effective Approach to the Story Cloze Test (N18-2)

Copied to clipboard

Siddarth Srinivasan, Richa Arora, Mark Riedl

An Annotated Corpus for Machine Reading of Instructions in Wet Lab Protocols (N18-2)

Challenge:	Existing approaches to the Cloze Test that use feature engineering to achieve high accuracy are ignoring the training set and training a model on the validation set.
Approach:	They propose a fully-neural approach to the Cloze Test using skip-thought embeddings of the stories in a feed-forward network that achieves close to state-of-the-art performance without any feature engineering.
Outcome:	The proposed approach achieves close to state-of-the-art performance on the Cloze Test without any feature engineering.

Copied to clipboard

Chaitanya Kulkarni, Wei Xu, Alan Ritter, Raghu Machiraju

Semantic Parsing

Challenge:	Existing efforts to annotate natural language instructions into machine-readable formats are limited.
Approach:	They propose to annotate a corpus of natural language instructions consisting of 622 wet lab protocols to facilitate automatic or semi-automatic conversion into a machine-readable format.
Outcome:	The proposed corpus can be used to facilitate automatic or semi-automatic conversion of protocols into a machine-readable format and benefit biological research.

Annotation Artifacts in Natural Language Inference Data (N18-2)

Copied to clipboard

Suchin Gururangan, Swabha Swayamdipta, Omer Levy, Roy Schwartz, Samuel Bowman, Noah A. Smith

Textual Inference

Challenge:	Large-scale datasets for natural language inference are created by crowdsourcing annotations . authors show that success of natural language models to date has been overestimated .
Approach:	They propose a method for crowdsourcing annotations to generate 3 new sentences based on a sentence (premise) they show that a simple text categorization model can correctly classify the hypothesis alone in about 67% of SNLI and 53% of MultiNLI .
Outcome:	The proposed model can classify the hypothesis alone in 67% of SNLI and 53% of MultiNLI datasets.

Humor Recognition Using Deep Learning (N18-2)

Copied to clipboard

Peng-Yu Chen, Von-Wun Soo

Reasoning

Challenge:	Humor is an essential but most fascinating element in personal communication.
Approach:	They propose a convolutional neural network with extensive filter size and filter number to increase the depth of networks.
Outcome:	The proposed model outperforms existing models on accuracy, precision and recall . the proposed model can learn to distinguish between humorous and nonhumorous texts .

Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection (N18-2)

Copied to clipboard

Jing Qian, Mai ElSherief, Elizabeth Belding, William Yang Wang

Reference-less Measure of Faithfulness for Grammatical Error Correction (N18-2)

Challenge:	Existing methods that focus on a single tweet as input are likely to yield high false positive and negative rates.
Approach:	They propose a model that leverages intra-user and inter-user representation learning to improve hate speech detection on Twitter by suppressing the noise in a single Tweet.
Outcome:	The proposed model significantly improves the f-score of a strong bidirectional LSTM model by 10.1%.

Copied to clipboard

Leshem Choshen, Omri Abend

Training Structured Prediction Energy Networks with Indirect Supervision (N18-2)

Challenge:	Existing reference-less measures (RLMs) for measuring grammaticality are expensive to collect and limited by the large number of valid outputs.
Approach:	They propose a semantic measure for Grammatical Error Correction that compares the semantic symbolic structure of the source and correction without relying on manually-curated references.
Outcome:	The proposed measure shows that it can be applied consistently to ungrammatical text, and that valid corrections obtain a high USim similarity score to the source, and invalid corrections get lower scores.

Copied to clipboard

Amirmohammad Rooshenas, Aishwarya Kamath, Andrew McCallum

Challenge:	a new rank-based training method for structured prediction energy networks is proposed . structured prediction is important in many domains, including computer vision, computational biology and natural language processing.
Approach:	They propose a rank-based training method for structured prediction energy networks . they use a scoring function defined with domain knowledge to train the models .
Outcome:	The proposed method minimizes ranking violation of the sampled structures with respect to a scalar scoring function defined with domain knowledge.

Si O No, Que Penses? Catalonian Independence and Linguistic Identity on Social Media (N18-2)

Copied to clipboard

Ian Stewart, Yuval Pinter, Jacob Eisenstein

Discourse & Pragmatics

Challenge:	This study examines the use of Catalan on Twitter in discourse related to the 2017 independence referendum.
Approach:	They use code-switching to determine the role of Catalan in political discourse . they corroborate prior findings that pro-independence tweets are more likely to include the local language than anti-independent tweets .
Outcome:	The proposed method corroborates previous findings that pro-independence tweets are more likely to include the local language than anti-independent tweets.

A Transition-Based Algorithm for Unrestricted AMR Parsing (N18-2)

Copied to clipboard

David Vilares, Carlos Gómez-Rodríguez

Analogies in Complex Verb Meaning Shifts: the Effect of Affect in Semantic Similarity Models (N18-2)

Challenge:	Abstract Meaning Representation (AMR) is a semantic representation language to map the meaning of English sentences into directed, cycled, labeled graphs.
Approach:	They propose a left-to-right non-projective transition-based parser that handles cycles and reentrancy natively within the transition system itself.
Outcome:	The proposed algorithm handles reentrancy and arbitrary cycles natively, i.e. within the transition system itself.

Copied to clipboard

Maximilian Köper, Sabine Schulte im Walde

Semantic Similarity

Challenge:	German particle verbs are complex verb structures that combine a prefix particle with a base verb.
Approach:	They propose a computational model to detect and distinguish analogies in meaning shifts between German base and complex verbs using a standard similarity model.
Outcome:	The proposed model detects and distinguishes analogies in meaning shifts between German base and complex verbs using a standard similarity model.

Character-Based Neural Networks for Sentence Pair Modeling (N18-2)

Copied to clipboard

Wuwei Lan, Wei Xu

Determining Event Durations: Models and Error Analysis (N18-2)

Challenge:	Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification and semantic textual similarity.
Approach:	They propose to use subwords to represent sentences without pretrained word embeddings . they find that subword models can achieve new state-of-the-art results without pretraining .
Outcome:	The proposed models can achieve state-of-the-art results on two social media datasets and competitive results on news data for paraphrase identification.

Copied to clipboard

Alakananda Vempala, Eduardo Blanco, Alexis Palmer

Challenge:	a crucial piece of information regarding events is their duration, a rarely mentioned attribute . core tasks such as temporal understanding and reasoning would benefit from knowing the expected duration of events.
Approach:	They introduce aspectual features that capture deeper linguistic information . they also experiment with neural networks to predict event durations .
Outcome:	The proposed models capture deeper linguistic information than previous work and provide useful clues.

Diachronic Usage Relatedness (DURel): A Framework for the Annotation of Lexical Semantic Change (N18-2)

Copied to clipboard

Dominik Schlechtweg, Sabine Schulte im Walde, Stefanie Eckmann

Challenge:	Existing frameworks for evaluating lexical semantic change are limited . evaluation of lexicals is a major obstacle in the field of semantic change detection .
Approach:	They propose a framework that extends synchronic polysemy annotation to diachronic changes in lexical meaning to counteract lack of resources for evaluating computational models of lexiconal semantic change.
Outcome:	The proposed framework exploits an intuitive notion of semantic relatedness and distinguishes between innovative and reductive meaning changes with high inter-annotator agreement.

Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings (N18-2)

Copied to clipboard

Yan Song, Shuming Shi, Jing Li, Haisong Zhang

Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model (N18-2)

Challenge:	Existing word embedding models are limited by semantic resources, which are hard to obtain or annotate.
Approach:	They propose a directional skip-gram model that explicitly distinguishes between left and right contexts in word prediction.
Outcome:	The proposed model outperforms other models on different datasets in semantic and syntactic evaluations.

Copied to clipboard

Goran Glavaš, Ivan Vulić

Challenge:	Existing methods to specialize distributional vectors to better reflect a particular relation are lacking in modern natural language processing.
Approach:	They propose a feed-forward neural architecture for discriminating between lexico-semantic relations . they propose to train relation classifiers using lexical relations from external resources .
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets and exhibits stable performance across languages.

Evaluating bilingual word embeddings on the long tail (N18-2)

Copied to clipboard

Fabienne Braune, Viktor Hangya, Tobias Eder, Alexander Fraser

Frustratingly Easy Meta-Embedding – Computing Meta-Embeddings by Averaging Source Word Embeddings (N18-2)

Challenge:	Bilingual word embeddings are useful for bilingual lexicon induction, but they focus on frequent words in general domains.
Approach:	They propose to evaluate bilingual word embeddings on rare words in different domains . they propose to use a multilingual dataset to build and combine BWEs based on a single word .
Outcome:	The proposed evaluations show that state-of-the-art methods fail on rare words . the proposed evaluation is based on a gold standard dataset and code .

Copied to clipboard

Joshua Coates, Danushka Bollegala

Introducing Two Vietnamese Datasets for Evaluating Semantic Models of (Dis-)Similarity and Relatedness (N18-2)

Challenge:	Existing methods for producing word embeddings have shown to produce accurate meta-embeddings from pre-trained source embeddables.
Approach:	They propose to use arithmetic mean of two distinct word embedding sets to produce an accurate meta-embedding.
Outcome:	The proposed method produces meta-embeddings comparable or better than more complex methods.

Copied to clipboard

Kim Anh Nguyen, Sabine Schulte im Walde, Ngoc Thang Vu

Semantic Similarity

Challenge:	Existing datasets for low-resource language Vietnamese assess semantic similarity . a dataset for word pairs with similarity levels is needed to evaluate these models .
Approach:	They present two new datasets for the low-resource language Vietnamese to assess models of semantic similarity.
Outcome:	The two datasets are comparable to the English datasets.

Lexical Substitution for Evaluating Compositional Distributional Models (N18-2)

Copied to clipboard

Maja Buljan, Sebastian Padó, Jan Šnajder

Challenge:	Compositional Distributional Semantic Models (CDSMs) model the meaning of phrases and sentences in vector space.
Approach:	They propose to use lexical substitution to evaluate CDSMs by comparing a LexSub-annotated corpus with a manual LexSub annotation.
Outcome:	The proposed model outperforms simple component-wise CDSMs and performs on par with the context2vec LexSub model using the same context.

Mittens: an Extension of GloVe for Learning Domain-Specialized Representations (N18-2)

Copied to clipboard

Nicholas Dingwall, Christopher Potts

Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds Using Paraphrases in a Neural Model (N18-2)

Challenge:	We show that the resulting representations can lead to faster learning and better results on a variety of tasks.
Approach:	They propose a simple extension of the GloVe representation learning model that starts with general-purpose representations and updates them based on specialized data sets.
Outcome:	The proposed model synthesizes general-purpose representations with specialized data while remaining faithful to the original space.

Copied to clipboard

Vered Shwartz, Chris Waterson

Omid Kashefi, Andrew T. Lucas, Rebecca Hwa

Challenge:	Recent work suggests that success stems from memorizing single prototypical words for each relation.
Approach:	They propose a neural paraphrasing approach that maps NCs to paraphrases that express the relation between constituent words.
Outcome:	The proposed method performs better when memorization is not possible.

Semantic Pleonasm Detection (N18-2)

Copied to clipboard

Challenge:	Pleonasms are words that are redundant.
Approach:	They propose an annotated corpus of semantic pleonasms and compare it against other corpus resources.
Outcome:	The proposed corpus is validated with interannotator agreement analyses and compares it with other corpus resources.

Copied to clipboard

Felipe Paula, Rodrigo Wilkens, Marco Idiart, Aline Villavicencio

Information Retrieval

Challenge:	Semantic Verbal Fluency tests have been used in the diagnosis of certain clinical conditions, like Dementia.
Approach:	They investigate three similarity measures for automatically identifying switches in semantic chains: semantic similarity from a manually constructed resource, word association strength and semantic relatedness, both calculated from corpora.
Outcome:	The proposed classifiers outperform those that use a gold standard taxonomy for clinical conditions.

Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees (N18-2)

Copied to clipboard

Ola Rønning, Daniel Hardt, Anders Søgaard

The Word Analogy Testing Caveat (N18-2)

Challenge:	sluice resolution in english is the problem of finding antecedents of wh-fronted ellipses . previous work relied on hand-crafted features over syntax trees that scale poorly to other languages and domains .
Approach:	They propose a model that uses partial parsing to find antecedents of wh-fronted ellipses in english . their model significantly outperforms previous work on available newswires .
Outcome:	The proposed model outperforms the only previous work on available newswires.

Copied to clipboard

Natalie Schluter

Transition-Based Chinese AMR Parsing (N18-2)

Challenge:	a number of word analogy tests are used to evaluate word embeddings . word embeds are used as a proxy for semantics and syntax à la Harris .
Approach:	They propose to use word embeddings as a proxy for distributional similarity . they propose to apply a transfer learning approach to word embeds to improve performance .
Outcome:	The proposed method improves performance across a wide range of NLP tasks.

Copied to clipboard

Chuan Wang, Bin Li, Nianwen Xue

Knowledge-Enriched Two-Layered Attention Network for Sentiment Analysis (N18-2)

Challenge:	Abstract Meaning Representation (AMR) is a semantic representation where the meaning of a sentence is encoded as a rooted, directed and acyclic graph.
Approach:	They propose a transition-based AMR parsing framework for Chinese to be used in the next generation of AMR.
Outcome:	The proposed parser is based on the Chinese AMR bank.

Copied to clipboard

Abhishek Kumar, Daisuke Kawahara, Sadao Kurohashi

Sentiment Analysis

Challenge:	Existing sentiment analysis systems are prone to word shortening, exaggeration, lack of grammar and appropriate punctuation.
Approach:	They propose a two-layered attention network based on Bidirectional Long Short-Term Memory for sentiment analysis using the Knowledge Graph Embedding generated using the WordNet.
Outcome:	The proposed model outperforms the state-of-the-art system on the benchmark dataset of SemEval 2017 Task 5 by 1.7 and 3.7 points respectively.

Letting Emotions Flow: Success Prediction by Modeling the Flow of Emotions in Books (N18-2)

Copied to clipboard

Suraj Maharjan, Sudipta Kar, Manuel Montes, Fabio A. González, Thamar Solorio

Sentiment Analysis

Challenge:	We obtained the best weighted F1-score of 69% for predicting books’ success in a multitask setting.
Approach:	They propose to model the flow of emotions over a book using recurrent neural networks and quantify its usefulness in predicting success in books.
Outcome:	The proposed model obtained the best weighted F1-score of 69% for predicting books’ success in a multitask setting.

Modeling Inter-Aspect Dependencies for Aspect-Based Sentiment Analysis (N18-2)

Copied to clipboard

Devamanyu Hazarika, Soujanya Poria, Prateek Vij, Gangeshwar Krishnamurthy, Erik Cambria, Roger Zimmermann

Multi-Task Learning Framework for Mining Crowd Intelligence towards Clinical Treatment (N18-2)

Challenge:	Present neural-based models exploit aspect and its contextual information in the sentence but ignore inter-aspect dependencies.
Approach:	They propose to combine aspect-based sentiment analysis with temporal dependency processing to incorporate this pattern into a sentence.
Outcome:	The proposed approach is based on the SemEval 2014 dataset and shows that it is effective for predicting sentiments of aspects in sentences with multiple aspects.

Copied to clipboard

Shweta Yadav, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya, Amit Sheth

Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-Based Sentiment Analysis (N18-2)

Challenge:	In recent past, social media has emerged as an active platform in the context of healthcare and medicine.
Approach:	They propose to use a novel adversarial learning approach to capture medical sentiments expressed in a medical blog to analyze the user's opinions on health-related issues.
Outcome:	The proposed framework can capture the user's opinions on health-related issues at a medical blog level.

Copied to clipboard

Fei Liu, Trevor Cohn, Timothy Baldwin

Sentiment Analysis

Challenge:	Recent work on target-dependent biLSTMs has shown that they are ineffective in aspect-based sentiment analysis.
Approach:	They propose a novel architecture that uses external memory chains with a delayed memory update mechanism to track entities.
Outcome:	The proposed model improves on a TABSA task using external memory chains with a delayed memory update mechanism.

Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation (N18-2)

Copied to clipboard

Roman Grundkiewicz, Marcin Junczys-Dowmunt

Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks (N18-2)

Challenge:	Currently, most effective GEC systems are based on phrase-based statistical machine translation.
Approach:	They combine two of the most popular approaches to automated Grammatical Error Correction (GEC) they create a hybrid GEC system that preserves the accuracy of SMT output and generates more fluent sentences .
Outcome:	The proposed system achieves state-of-the-art on the CoNLL-2014 and JFLEG benchmarks.

Copied to clipboard

Salman Mohammed, Peng Shi, Jimmy Lin

Looking for Structure in Lexical and Acoustic-Prosodic Entrainment Behaviors (N18-2)

Challenge:	Existing work on simple question answering over knowledge graphs involves increasingly complex NN architectures.
Approach:	They propose to decompose the problem into entity detection, entity linking, relation prediction, evidence combination and heuristics.
Outcome:	The proposed approach outperforms existing models and benchmarks on a simple QA task.

Copied to clipboard

Andreas Weise, Rivka Levitan

Linguistics & Cognitive NLP

Challenge:	Entrainment is the tendency of human interlocutors to adapt their behavior to each other to become more similar.
Approach:	They propose to use acoustic-prosodic and lexical entrainment to measure speakers' overall entraining behaviors and search for an underlying structure.
Outcome:	The proposed method does not find any significant correlations, clusters, or principal components in various entrainment measures.

Modeling Semantic Plausibility by Injecting World Knowledge (N18-2)

Copied to clipboard

Su Wang, Greg Durrett, Katrin Erk

Challenge:	Existing models for semantic plausibility are based on distributional data, but injecting knowledge about entity properties provides a substantial performance boost.
Approach:	They propose to inject manually elicited knowledge about entity properties into a dataset to improve plausibility models.
Outcome:	The proposed dataset is a great testbed for semantic plausibility models . it shows that injection of knowledge about entity properties improves performance .

A Bi-Model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling (N18-2)

Copied to clipboard

Yu Wang, Yilin Shen, Hongxia Jin

A Comparison of Two Paraphrase Models for Taxonomy Augmentation (N18-2)

Challenge:	Intent detection and slot filling are two main tasks for building a spoken language understanding system.
Approach:	They propose to use a sequence to sequence model to generate both intent and slot filling tasks together to perform the two tasks jointly.
Outcome:	The proposed model achieves 0.5% intent accuracy improvement and 0.9 % slot filling improvement on the ATIS benchmark data.

Copied to clipboard

Vassilis Plachouras, Fabio Petroni, Timothy Nugent, Jochen L. Leidner

A Laypeople Study on Terminology Identification across Domains and Task Definitions (N18-2)

Challenge:	a taxonomy is often used to look up concepts in text documents.
Approach:	They compare two state-of-the-art paraphrase models with a paraphrase dataset . they find that paraphrasing is a viable method to augment taxonomies with more terms .
Outcome:	The proposed model outperforms the previous model on the risk domain.

Copied to clipboard

Anna Hätty, Sabine Schulte im Walde

Challenge:	Existing studies on term annotation show that even experts differ in their understanding of termhood .
Approach:	They propose a new dataset of term annotation that examines the common understanding of what constitutes a term.
Outcome:	The proposed datasets show that even experts differ in their understanding of termhood . the findings suggest that there is a common understanding of what constitutes a term .

A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network (N18-2)

Copied to clipboard

Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh Phung

Cross-language Article Linking Using Cross-Encyclopedia Entity Embedding (N18-2)

Challenge:	Existing knowledge base embedding models are incomplete, i.e., missing a lot of valid triples.
Approach:	They propose a convolutional neural network embedding model for knowledge base completion that captures global relationships and transitional characteristics.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets.

Copied to clipboard

Chun-Kai Wu, Richard Tzong-Han Tsai

Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations (N18-2)

Challenge:	Existing methods to create interlanguage links between encyclopedias are time-consuming and difficult.
Approach:	They propose a method to find corresponding article pairs of different languages in encyclopedias by cross-encyclopae entity embedding.
Outcome:	The proposed method improves performance over baseline by 29.62% compared to the current best system.

Copied to clipboard

Prafulla Kumar Choubey, Kaushik Raju, Ruihong Huang

Improve Neural Entity Recognition via Multi-Task Data Selection and Constrained Decoding (N18-2)

Challenge:	Identifying the most dominant and central event of a document is useful for many applications, says a new study . identifying the most prominent event in a news article is useful in text summarization, storyline generation and text segmentation.
Approach:	They propose to detect the most dominant and central event of a document . central event usually has many coreferential event mentions scattered throughout document a .
Outcome:	The proposed task can detect the most dominant and central event in a document . it can be used for text summarization, storyline generation and text segmentation .

Copied to clipboard

Huasha Zhao, Yi Yang, Qiong Zhang, Luo Si

Low-Resource NLP

Challenge:	Entity recognition is a widely benchmarked task in natural language processing . a neural architecture called BiLSTM-CRF is used to model the language sequences .
Approach:	They propose a neural architecture called BiLSTM-CRF to model the language sequences.
Outcome:	The proposed system achieves state-of-the-art on English entity recognition task and also in other languages.

Keep Your Bearings: Lightly-Supervised Information Extraction with Ladder Networks That Avoids Semantic Drift (N18-2)

Copied to clipboard

Ajay Nagesh, Mihai Surdeanu

Semi-Supervised Event Extraction with Paraphrase Clusters (N18-2)

Challenge:	Using ladder networks, semi-supervised learning can be iterative and drifts semantically as learning progresses.
Approach:	They propose a method that uses ladder networks to perform a task of named entity classification using a large, unannotated dataset.
Outcome:	The proposed method improves on two standard datasets for named entity classification.

Copied to clipboard

James Ferguson, Colin Lockard, Daniel Weld, Hannaneh Hajishirzi

Structure Regularized Neural Network for Entity Relation Classification for Chinese Literature Text (N18-2)

Challenge:	Existing event extraction systems are limited in their accuracy due to the lack of available training data.
Approach:	They propose a method for self-training event extraction systems by bootstrapping additional training data.
Outcome:	The proposed method improves on ACE 2005 and TAC-KBP 2015 datasets.

Copied to clipboard

Ji Wen, Xu Sun, Xuancheng Ren, Qi Su

Syntactic Patterns Improve Information Extraction for Medical Search (N18-2)

Challenge:	Existing methods for relation classification have been used in natural language processing.
Approach:	They propose a relation classification task for Chinese literature text using a new dataset.
Outcome:	The proposed model outperforms the state-of-the-art methods on Chinese literature text.

Copied to clipboard

Roma Patel, Yinfei Yang, Iain Marshall, Ani Nenkova, Byron Wallace

Information Retrieval

Challenge:	Medical professionals search the literature by specifying the type of patients, the medical intervention(s) and the outcome measure(s).
Approach:	They propose to exploit the availability of structured abstracts to extract medically relevant information from syntactic patterns.
Outcome:	The proposed models differ from the constituent unigrams in the extracted patterns, suggesting that they capture contextual information that is otherwise lost.

Syntactically Aware Neural Architectures for Definition Extraction (N18-2)

Copied to clipboard

Luis Espinosa-Anke, Steven Schockaert

A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing (N18-2)

Challenge:	Existing approaches to identify definitional knowledge in text corpora are based on Wikipedia-like definitions.
Approach:	They propose to combine Convolutional and Recurrent Neural Networks to train definitional knowledge in text corpora.
Outcome:	The proposed models can be applied to more noisy domain-specific corpora.

Copied to clipboard

Daniel Fernández-González, Carlos Gómez-Rodríguez

Are Automatic Methods for Cognate Detection Good Enough for Phylogenetic Reconstruction in Historical Linguistics? (N18-2)

Challenge:	Existing dynamic oracles for greedy parsers can handle non-projective syntax, but none are available for these types of training.
Approach:	They propose an efficient dynamic oracle for training the 2-Planar transition-based parser with over 99% coverage on non-projective syntactic corpora.
Outcome:	The proposed model outperforms the static training strategy in the vast majority of languages tested and scored better on most datasets than the arc-hybrid parser enhanced with the Swap transition.

Copied to clipboard

Taraka Rama, Johann-Mattis List, Johannes Wahle, Gerhard Jäger

Challenge:	Phylogenetic trees are hypotheses of how sets of related languages evolved in time.
Approach:	They compare the performance of automatic cognate detection algorithms to classical manually annotated cognate sets.
Outcome:	The proposed methods perform better than classically annotated cognate sets . future work on phylogenetic reconstruction can profit from the results .

Automatically Selecting the Best Dependency Annotation Design with Dynamic Oracles (N18-2)

Copied to clipboard

Guillaume Wisniewski, Ophélie Lacroix, François Yvon

Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning (N18-2)

Challenge:	Multiple annotation conventions have been proposed for representing dependency structures.
Approach:	They propose to consider a set of syntactic references encoding alternative syntak representations to train a parser with a dynamic oracle.
Outcome:	The proposed approach can predict the best syntactic representation among all possible references.

Copied to clipboard

Masashi Yoshikawa, Koji Mineshima, Hiroshi Noji, Daisuke Bekki

Reasoning

Challenge:	Existing methods to recognize textual entailment use a CCG parser to process sentences . failing to recognize the similar syntactic structure results in inconsistent argument structures .
Approach:	They propose to extend existing CCG parsers to parse sentences consistently . they use an inter-sentence modeling with Markov Random Fields to achieve this .
Outcome:	The proposed method improves on English and Japanese languages.

Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees (N18-2)

Copied to clipboard

Lauriane Aufrant, Guillaume Wisniewski, François Yvon

Improving Coverage and Runtime Complexity for Exact Inference in Non-Projective Transition-Based Dependency Parsers (N18-2)

Challenge:	Several strategies have been proposed to overcome the projectivity constraint by introducing transition-based dependency parsers that can build non-projective dependencies.
Approach:	They propose a modification of dynamic oracles to allow use of non-projective data . their method consistently outperforms traditional projectivization and pseudo-projectivisation approaches .
Outcome:	The proposed method outperforms projectivization and pseudo-projectivisation methods on 73 treebanks and achieves significant gains for non-projective languages.

Copied to clipboard

Tianze Shi, Carlos Gómez-Rodríguez, Lillian Lee

Towards a Variability Measure for Multiword Expressions (N18-2)

Challenge:	Non-projective dependency trees account for 12.59% of all training sentences in the annotated Universal Dependencies (UD) 2.1 data.
Approach:	They generalize Cohen et al.'s (2011) parser to a family of non-projective transition-based dependency parsers allowing polynomial-time exact inference.
Outcome:	The proposed system can be extended to include a variant that reduces time complexity to O(n6), improving over the known bounds in exact inference for non-projective transition-based parsing.

Copied to clipboard

Caroline Pasquer, Agata Savary, Jean-Yves Antoine, Carlos Ramisch

Defoiling Foiled Image Captions (N18-2)

Challenge:	Multiword expressions (MWEs) are groups of words whose meaning does not derive from the meaning of their components and from their syntactic structure in a regular way.
Approach:	They propose to use a language-independent measure of variability dedicated to verbal MWEs based on syntactic and discontinuity-related clues to assess its relevance with respect to a linguistic benchmark.
Outcome:	The proposed measure is useful for VMWE classification and variant identification on a French corpus.

Copied to clipboard

Pranava Swaroop Madhyastha, Josiah Wang, Lucia Specia

Pragmatically Informative Image Captioning with Character-Level Inference (N18-2)

Challenge:	Existing models for vision-to-language tasks do not understand images sufficiently, despite their impressive performance.
Approach:	They propose to use explicit object information to solve foiled caption detection problem . they propose to replace a word in caption with a semantically similar word .
Outcome:	The proposed model achieves state-of-the-art on a recently published dataset with scores exceeding those achieved by humans on the task.

Copied to clipboard

Reuben Cohn-Gordon, Noah Goodman, Christopher Potts

Object Ordering with Bidirectional Matchings for Visual Reasoning (N18-2)

Challenge:	a neural image captioner and a Rational Speech Acts (RSA) model are pragmatically informative . previous attempts to combine RSA with neural image-captioning require an inference which normalizes over the entire set of possible utterances.
Approach:	They propose a neural image captioner with a Rational Speech Acts model to make it pragmatically informative.
Outcome:	The proposed system outperforms a non-pragmatic baseline and word-level RSA captioner on a word-based model.

Copied to clipboard

Hao Tan, Mohit Bansal

Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations (N18-2)

Challenge:	et al. (2016) proposed a novel end-to-end neural model for visual reasoning with compositional natural language instructions.
Approach:	They propose an end-to-end neural model for a visual reasoning task based on a newly-released Cornell dataset . they use joint bidirectional attention to build a two-way conditioning between visual information and language phrases . then they use an RL-based pointer network to sort and process the varying number of unordered objects in each image and pool over the three decisions .
Outcome:	The proposed model achieves 4-6% absolute improvements over the state-of-the-art model on the NLVR dataset.

Copied to clipboard

Sosuke Kobayashi

Language Models

Challenge:	Neural network-based models for NLP have been growing with state-of-the-art results in various tasks.
Approach:	They propose a data augmentation method for labeled sentences called contextual augmentation.
Outcome:	The proposed method improves classifiers based on convolutional or recurrent neural networks.

Cross-Lingual Learning-to-Rank with Shared Representations (N18-2)

Copied to clipboard

Shota Sasaki, Shuo Sun, Shigehiko Schamoni, Kevin Duh, Kentaro Inui

Self-Attention with Relative Position Representations (N18-2)

Challenge:	Cross-lingual information retrieval (CLIR) is a document retrieval task where the documents are written in a language different from that of the user's query.
Approach:	They propose a large-scale dataset derived from Wikipedia to support CLIR research in 25 languages.
Outcome:	The proposed model can improve the results of Swahili-English CLIR in Japanese and Japanese.

Copied to clipboard

Peter Shaw, Jakob Uszkoreit, Ashish Vaswani

Text Segmentation as a Supervised Learning Task (N18-2)

Challenge:	Recent approaches to sequence to sequence learning leverage recurrence, convolution, attention or combination of recurrent and convolutional neural networks.
Approach:	They propose an approach that extends the self-attention mechanism to consider representations of relative positions, or distances between sequence elements.
Outcome:	The proposed approach yields 1.3 BLEU and 0.3 BLUE on translation tasks . it is based on a relation-aware self-attention mechanism that can generalize to arbitrary graph-labeled inputs.

Copied to clipboard

Omri Koshorek, Adir Cohen, Noam Mor, Michael Rotman, Jonathan Berant

What’s in a Domain? Learning Domain-Robust Text Representations using Adversarial Training (N18-2)

Challenge:	Existing datasets for text segmentation are small in size and do not represent the natural distribution of text in documents.
Approach:	They propose a large dataset for text segmentation that is automatically extracted and labeled from Wikipedia and develop a model based on this dataset.
Outcome:	The proposed model generalizes well to unseen natural text.

Copied to clipboard

Yitong Li, Timothy Baldwin, Trevor Cohn

Robustness in NLP

Challenge:	a key roadblock is application to new domains, unseen in training.
Approach:	They propose a method to optimise in- and out-of-domain accuracy by combing domain-specific and domain-general components with adversarial training for domain.
Outcome:	The proposed method improves on domain adaptation and domain-adversarial training.

Automated Paraphrase Lattice Creation for HyTER Machine Translation Evaluation (N18-2)

Copied to clipboard

Marianna Apidianaki, Guillaume Wisniewski, Anne Cocos, Chris Callison-Burch

Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks (N18-2)

Challenge:	Existing machine translation evaluation metrics use synonyms and paraphrases to reward meaning-equivalent but lexically divergent translations.
Approach:	They propose a machine translation evaluation metric which exploits reference translations enriched with meaning equivalent expressions.
Outcome:	The proposed metric achieves medium performance on large and noisier datasets . it is compared with the existing HyTER evaluation metric .

Copied to clipboard

Diego Marcheggiani, Jasmijn Bastings, Ivan Titov

Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation (N18-2)

Challenge:	Semantic representations have long been argued as potentially useful for enforcing meaning preservation and improving generalization performance of machine translation methods.
Approach:	They propose to integrate semantic representations into neural machine translation by injecting a semantic bias into sentence encoders and achieving improvements in BLEU scores.
Outcome:	The proposed representations achieve better BLEU scores over the linguistic-agnostic and syntax-aware versions on the English–German language pair.

Copied to clipboard

Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Stephan Vogel

Learning Hidden Unit Contribution for Adapting Neural Machine Translation Models (N18-2)

Challenge:	a tunable agent decides the best segmentation strategy for a user-defined BLEU loss and Average Proportion (AP) constraint.
Approach:	They propose a tunable agent which decides the best segmentation strategy for a user-defined BLEU loss and average proportion (AP) constraint.
Outcome:	The proposed agent outperforms existing Wait-if-diff and Wait-If-worse agents on BLEU with a lower latency.

Copied to clipboard

David Vilar

Neural Machine Translation Decoding with Terminology Constraints (N18-2)

Challenge:	In this paper we explore the use of Learning Hidden Unit Contribution for neural machine translation.
Approach:	They propose to use Learning Hidden Unit Contribution for the task of neural machine translation.
Outcome:	The proposed method achieves improvements of up to 2.6 BLEU points over a general system . it also achieves up to 6 BLUE points if the initial system has been trained on out-of-domain data .

Copied to clipboard

Eva Hasler, Adrià de Gispert, Gonzalo Iglesias, Bill Byrne

On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference (N18-2)

Challenge:	Constrained neural machine translation systems can provide excellent quality but do not strictly enforce terminology.
Approach:	They propose a framework for constrained neural decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans.
Outcome:	The proposed framework performs well on multiple translation tasks and motivates the need for constrained decoding with attentions to reduce misplacement and duplication when translating user constraints.

Copied to clipboard

Adam Poliak, Yonatan Belinkov, James Glass, Benjamin Van Durme

Using Word Vectors to Improve Word Alignments for Low Resource Machine Translation (N18-2)

Challenge:	Existing methods to investigate whether sentence representations from NMT systems capture distinct semantic phenomena are limited.
Approach:	They propose a process to investigate the extent to which sentence representations arising from neural machine translation systems encode distinct semantic phenomena.
Outcome:	The proposed model is suited to supporting inferences at the syntax-semantics interface, compared to anaphora resolution requiring world knowledge.

Copied to clipboard

Nima Pourdamghani, Marjan Ghazvininejad, Kevin Knight

When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation? (N18-2)

Challenge:	Using word similarities, we improve word alignments in low resource settings . word alignment is essential for statistical machine translation (MT)
Approach:	They propose a method for improving word alignments using word similarities using word vectors trained on monolingual data.
Outcome:	The proposed method improves word alignments in low-resource settings by improving alignments of infrequent tokens.

Copied to clipboard

Ye Qi, Devendra Sachan, Matthieu Felix, Sarguna Padmanabhan, Graham Neubig

Are All Languages Equally Hard to Language-Model? (N18-2)

Challenge:	Pre-trained word embeddings have proven to be invaluable for improving performance in natural language analysis tasks where large-scale parallel corpora cannot be obtained.
Approach:	They perform five sets of experiments to analyze when pre-trained word embeddings can be useful in NMT tasks.
Outcome:	The embeddings provide gains of up to 20 BLEU points in the most favorable setting.

Copied to clipboard

Ryan Cotterell, Sabrina J. Mielke, Jason Eisner, Brian Roark

The Computational Complexity of Distinctive Feature Minimization in Phonology (N18-2)

Challenge:	a fair comparison of language models is tricky because of the size of the corpora and the variability of orthographic systems.
Approach:	They propose a framework for fair cross-linguistic comparison of language models . they show that in some languages, textual expression is harder to predict with n-gram models compared to LSTM models based on translated text .
Outcome:	The proposed framework is based on translated text and language models on 21 languages.

Copied to clipboard

Hubie Chen, Mans Hulden

Unsupervised Disambiguation of Syncretism in Inflected Lexicons (N18-2)

Challenge:	a standard assumption in phonology is that finding a minimal feature specification is an automatic part of acquisition and generalization.
Approach:	They analyze the problem of determining whether a set of phonemes forms a natural class and find the minimal feature specification for the class.
Outcome:	The proposed model is based on a greedy algorithm that fails to find minimal features . the proposed model can be used to find features that are universal across languages .

Copied to clipboard

Ryan Cotterell, Christo Kirov, Sabrina J. Mielke, Jason Eisner

Contextualized Word Representations for Reading Comprehension (N18-2)

Challenge:	Lexical ambiguity makes it difficult to compute useful statistics of a corpus.
Approach:	They propose a neural network-based model that fits a prior distribution over feature bundles to a list of unigram type counts and partitions each count among different analyses of that unigrammer.
Outcome:	The proposed model is based on a list of unigram type counts and partitions each count among different analyses of that unigrammer.

Copied to clipboard

Shimi Salant, Jonathan Berant

Crowdsourcing Question-Answer Meaning Representations (N18-2)

Challenge:	Reading comprehension (RC) is a high-level task in natural language understanding that requires reading a document and answering questions about its content.
Approach:	They propose to provide a standard neural network for reading a document and answering a question about its content.
Outcome:	The proposed model improves on the competitive SQuAD dataset by providing rich contextualized word representations and allowing it to choose between context-dependent and context-independent representations.

Copied to clipboard

Julian Michael, Gabriel Stanovsky, Luheng He, Ido Dagan, Luke Zettlemoyer

Leveraging Context Information for Natural Question Generation (N18-2)

Challenge:	Existing datasets for predicate-argument relationships are lacking highly skilled and trained annotators.
Approach:	They propose a crowdsourcing scheme to generate question-answer pairs that represent predicate-argument relationships in sentences as a set of question-announcer pairs.
Outcome:	The proposed model covers the vast majority of predicate-argument relationships in existing datasets along with many previously under-resourced ones, including implicit arguments and relations.

Copied to clipboard

Linfeng Song, Zhiguo Wang, Wael Hamza, Yue Zhang, Daniel Gildea

Robust Machine Comprehension Models via Adversarial Training (N18-2)

Challenge:	Existing work for natural question generation ignores the input passage or hard-codes answer positions.
Approach:	They propose a model that matches the answer with the passage before generating a question.
Outcome:	The proposed model outperforms the state-of-the-art model using rich features.

Copied to clipboard

Yicheng Wang, Mohit Bansal

Robustness in NLP

Challenge:	Existing models for the Stanford Question Answering Dataset suffer from a 50% decrease in F1 score during adversarial evaluation based on AddSent.
Approach:	They propose an alternative adversary-generation algorithm, AddSentDiverse, that significantly increases the variance within the adversarial training data by providing effective examples that punish the model for making certain superficial assumptions.
Outcome:	The proposed algorithm can achieve a 36.5% increase in F1 score while maintaining performance on the regular SQuAD task.

Simple and Effective Semi-Supervised Question Answering (N18-2)

Copied to clipboard

Bhuwan Dhingra, Danish Danish, Dheeraj Rajagopal

TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation (N18-2)

Challenge:	Existing deep learning systems for extractive Question Answering are limited and expensive to construct.
Approach:	They propose a semi-supervised QA system where end user specifies a set of documents and only a few labelled examples.
Outcome:	The proposed system achieves 50% F1 score on SQuAD and TriviaQA with very little labeled data.

Copied to clipboard

Tao Yu, Zifan Li, Zilin Zhang, Rui Zhang, Dragomir Radev

Programming Languages in NLP

Challenge:	Existing systems that can understand natural language questions and generate corresponding SQL queries are not able to do this.
Approach:	They propose a novel approach which formats the problem as a slot filling task in a more reasonable way and utilizes type information to better understand rare entities and numbers in the questions.
Outcome:	The proposed approach outperforms the prior art on the WikiSQL dataset and can reach 82.6% accuracy, a 17.5% improvement compared to the previous content-sensitive model.

Community Member Retrieval on Social Media Using Textual Information (N18-2)

Copied to clipboard

Aaron Jaech, Shobhit Hathi, Mari Ostendorf

Cross-Domain Review Helpfulness Prediction Based on Convolutional Neural Networks with Auxiliary Domain Discriminators (N18-2)

Challenge:	Existing methods for community membership detection using only text features are not effective.
Approach:	They propose an unsupervised task for learning user embeddings using text features . they propose a proxy task for embeddables that uses two embeddibles from the same account .
Outcome:	The proposed model is more effective than unsupervised representations of user embeddings with 16 different communities.

Copied to clipboard

Cen Chen, Yinfei Yang, Jun Zhou, Xiaolong Li, Forrest Sheng Bao

Challenge:	Recent studies on review helpfulness prediction require labeled samples for each domain/category of interest.
Approach:	They propose a convolutional neural network based model which leverages word-level and character-based representations to transfer knowledge between domains.
Outcome:	The proposed model outperforms the state-of-the-art on the Amazon product review dataset.

Predicting Foreign Language Usage from English-Only Social Media Posts (N18-2)

Copied to clipboard

Svitlana Volkova, Stephen Ranshous, Lawrence Phillips

A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents (N18-2)

Challenge:	Social media is known for its multi-cultural and multilingual interactions, a natural product of which is code-mixing.
Approach:	They analyze 6 million tweets produced by 27 thousand multilingual users speaking 12 other languages besides English to build predictive models to infer non-English languages users speak exclusively from their tweets.
Outcome:	The proposed models are based on a corpus of 6 million tweets produced by 27 thousand multilingual users speaking 12 other languages besides English . they show that content, style and syntax are the most predictive of non-English languages that users speak on Twitter.

Copied to clipboard

Arman Cohan, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Seokhwan Kim, Walter Chang, Nazli Goharian

Summarization

Challenge:	Existing abstractive summarization models focus on summarizing sentences and short documents.
Approach:	They propose a hierarchical encoder that models the discourse structure of a document, and an attentive discourse-aware decoder to generate the summary.
Outcome:	The proposed model significantly outperforms state-of-the-art models on two large-scale datasets of scientific papers.

A Mixed Hierarchical Attention Based Encoder-Decoder Approach for Standard Table Summarization (N18-2)

Copied to clipboard

Parag Jain, Anirban Laha, Karthik Sankaranarayanan, Preksha Nema, Mitesh M. Khapra, Shreyas Shetty

Effective Crowdsourcing for a New Type of Summarization Task (N18-2)

Challenge:	Structured data summarization involves generation of summaries from structured input data.
Approach:	They propose a hierarchical attention-based encoder-decoder model which leverages the structure in addition to the content of the tables.
Outcome:	The proposed model improves on the weathergov dataset by 30% over the current state-of-the-art.

Copied to clipboard

Youxuan Jiang, Catherine Finegan-Dollak, Jonathan K. Kummerfeld, Walter Lasecki

Key2Vec: Automatic Ranked Keyphrase Extraction from Scientific Articles using Phrase Embeddings (N18-2)

Challenge:	Currently, summarization research focuses on summarizing the entire text, but in practice, readers are often interested in only one aspect of the document or conversation.
Approach:	They propose a new task where the goal is to summarize a particular aspect of a document.
Outcome:	The proposed task is based on a crowdsourced data collection workflow that allows users to collect high-quality summaries.

Copied to clipboard

Debanjan Mahata, John Kuriakose, Rajiv Ratn Shah, Roger Zimmermann

Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata (N18-2)

Challenge:	Keyphrase extraction is a fundamental task in natural language processing that facilitates mapping of documents to a set of representative phrases.
Approach:	They propose an unsupervised technique that leverages phrase embeddings for ranking keyphrases extracted from scientific articles using theme-weighted PageRank.
Outcome:	The proposed method performs better on benchmark datasets than other methods and is of high quality.

Copied to clipboard

Lucie-Aimée Kaffee, Hady Elsahar, Pavlos Vougiouklis, Christophe Gravier, Frédérique Laforest, Jonathon Hare, Elena Simperl

Challenge:	Existing Wikipedia content is unevenly distributed among 287 languages . authors propose a neural network architecture that generates textual summaries from Wikidata triples .
Approach:	They propose an automated approach to generate Wikipedia summaries from Wikidata triples using structured data.
Outcome:	The proposed approach is tested on Arabic and Esperanto languages with limited editors and content in the most under-resourced Wikipedias.

Multi-Reward Reinforced Summarization with Saliency and Entailment (N18-2)

Copied to clipboard

Ramakanth Pasunuru, Mohit Bansal

Objective Function Learning to Match Human Judgements for Optimization-Based Summarization (N18-2)

Challenge:	Abstractive text summarization is the task of compressing and rewriting a long document into a short summary while maintaining saliency, directed logical entailment, and non-redundancy.
Approach:	They propose a novel reward function for ROUGESal and Entail to improve abstractive summarization . they use a coverage-based reward function to combine ROUGE and En Tail .
Outcome:	The proposed method achieves state-of-the-art results on CNN/Daily Mail dataset and strong improvements in a test-only transfer setup on DUC-2002.

Copied to clipboard

Maxime Peyrard, Iryna Gurevych

Pruning Basic Elements for Better Automatic Evaluation of Summaries (N18-2)

Challenge:	In previous work on summarization, the objective function is based on ad-hoc assumptions about which quality aspects of a summary are relevant.
Approach:	They learn a summary-level scoring function including human judgments as supervision and automatically generated data as regularization.
Outcome:	The proposed method performs well across automatic and manual evaluations.

Copied to clipboard

Ukyo Honda, Tsutomu Hirao, Masaaki Nagata

Summarization

Challenge:	Summarization studies work on increasing the scores that are given by automatic evaluation measures.
Approach:	They propose a simple but highly effective automatic evaluation measure of summarization, pruned Basic Elements.
Outcome:	The proposed measure outperforms ROUGE and BE in most cases and achieves highest correlation coefficient in TAC 2011 AESOP task.

Unsupervised Keyphrase Extraction with Multipartite Graphs (N18-2)

Copied to clipboard

Florian Boudin

Where Have I Heard This Story Before? Identifying Narrative Similarity in Movie Remakes (N18-2)

Challenge:	Recent years have witnessed a resurgence of interest in automatic keyphrase extraction.
Approach:	They propose an unsupervised keyphrase extraction model that encodes topical information within a multipartite graph structure.
Outcome:	The proposed model improves on three widely used datasets.

Copied to clipboard

Snigdha Chaturvedi, Shashank Srivastava, Dan Roth

Challenge:	Existing methods to identify instances of similar narratives are limited by annotated data.
Approach:	They propose a task for identifying instances of similar narratives from a collection of narrative texts.
Outcome:	The proposed approach yields an 8% absolute improvement over a baseline on a novel dataset of plot summaries of 577 movie remakes from Wikipedia.

Multimodal Emoji Prediction (N18-2)

Copied to clipboard

Francesco Barbieri, Miguel Ballesteros, Francesco Ronzano, Horacio Saggion

Higher-Order Coreference Resolution with Coarse-to-Fine Inference (N18-2)

Challenge:	Emojis are small images that are commonly included in social media text messages.
Approach:	They propose a multimodal approach that is able to predict emojis in Instagram posts by using both text and image.
Outcome:	The proposed model incorporates both text and image to improve accuracy .

Copied to clipboard

Kenton Lee, Luheng He, Luke Zettlemoyer

Non-Projective Dependency Parsing with Non-Local Transitions (N18-2)

Challenge:	a new approach to coreference resolution uses a span-ranking architecture as an attention mechanism to iteratively refine span representations.
Approach:	They propose a fully-differentiable approximation to higher-order inference for coreference resolution . they propose introducing a coarse-to-fine approach that incorporates a less accurate but more efficient bilinear factor .
Outcome:	The proposed model significantly improves accuracy on the English OntoNotes benchmark while being far more computationally efficient.

Copied to clipboard

Daniel Fernández-González, Carlos Gómez-Rodríguez

Detecting Linguistic Characteristics of Alzheimer’s Dementia by Interpreting Neural Models (N18-2)

Challenge:	Existing greedy transition-based parsers are prone to error propagation when creating arcs involving multiple transitions.
Approach:	They propose a greedy transition-based parser that introduces non-local transitions that create arcs involving nodes to the left of the current focus positions.
Outcome:	The proposed system outperforms the original version and achieves the best accuracy on the Stanford Dependencies conversion of the Penn Treebank among greedy transition-based parsers.

Copied to clipboard

Sweta Karlekar, Tong Niu, Mohit Bansal

Deep Dungeons and Dragons: Learning Character-Action Interactions from Role-Playing Game Transcripts (N18-2)

Challenge:	Current diagnoses often involve lengthy medical evaluations.
Approach:	They apply neural models based on CNNs, LSTM-RNNs, and their combination to classify AD and control language samples.
Outcome:	The proposed model achieves independent benchmark accuracy for the AD classification task.

Copied to clipboard

Annie Louis, Charles Sutton

Challenge:	a novel approach to understanding narratives involves modelling the interaction between characters and actions . we propose role-playing games as a testbed for inferring interactions between characters in narratives .
Approach:	They propose role-playing games as a testbed for learning latent ties between characters and actions . they propose to combine character and action descriptions from online discussion forums .
Outcome:	The proposed model can capture interactions between characters and actions in narratives . it can predict actions better when character attributes are taken into account .

Feudal Reinforcement Learning for Dialogue Management in Large Domains (N18-2)

Copied to clipboard

Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su, Stefan Ultes, Lina M. Rojas-Barahona, Bo-Hsiang Tseng, Milica Gašić

Natural Language Interfaces

Challenge:	Reinforcement learning (RL) is a promising approach to model dialogue policy optimisation but fails to scale to large domains due to the curse of dimensionality.
Approach:	They propose a novel approach to dialogue policy optimisation using reinforcement learning . they propose to decompose the decision into two steps using a domain ontology .
Outcome:	The proposed architecture outperforms state-of-the-art in several dialogue domains without any additional reward signal.

Evaluating Historical Text Normalization Systems: How Well Do They Generalize? (N18-2)

Copied to clipboard

Alexander Robertson, Sharon Goldwater

Gated Multi-Task Network for Text Classification (N18-2)

Challenge:	Historical text normalization systems aim to convert historical wordforms to their modern equivalents . many of these systems have been developed and tested on a single language .
Approach:	They propose to use a nave baseline system to evaluate historical text normalization systems . they show that the models generalize well to unseen words in tests on five languages .
Outcome:	The proposed models generalize well to unseen words on five languages, but provide no clear benefit over the nave baseline.

Copied to clipboard

Liqiang Xiao, Honglun Zhang, Wenqing Chen

Natural Language to Structured Query Generation via Meta-Learning (N18-2)

Challenge:	Existing approaches to multitask learning share the features without distinguishing the usefulness of the features, generating undesired interference between tasks.
Approach:	They propose to introduce a gate mechanism into multi-task CNN and propose a new gated sharing unit which can filter the feature flows between tasks and greatly reduce the interference.
Outcome:	The proposed approach can learn selection rules automatically and gain a great improvement over strong baselines.

Copied to clipboard

Po-Sen Huang, Chenglong Wang, Rishabh Singh, Wen-tau Yih, Xiaodong He

Smaller Text Classifiers with Discriminative Cluster Embeddings (N18-2)

Challenge:	Conventional supervised training is a pervasive paradigm for NLP problems . however, examples of the same problem may vary widely . a few-shot meta-learning scenario is used to learn multiple models .
Approach:	They propose a learning protocol that treats each example as a unique pseudo-task . they use a few-shot meta-learning scenario to reduce the original learning problem to a single example .
Outcome:	The proposed learning protocol achieves 1.1%–5.4% accuracy gains over non-meta-learning counterparts on a WikiSQL dataset.

Copied to clipboard

Mingda Chen, Kevin Gimpel

Role-specific Language Models for Processing Recorded Neuropsychological Exams (N18-2)

Challenge:	Word embeddings dominate overall model sizes in neural methods for natural language processing, especially when large vocabularies and high dimensions are used.
Approach:	They propose a Gumbel-Softmax distribution to maximize over the latent clustering while minimizing the task loss.
Outcome:	The proposed method minimizes the task loss while maximizing over the latent clustering while remaining parameter-efficient.

Copied to clipboard

Tuka Al Hanai, Rhoda Au, James Glass

Slot-Gated Modeling for Joint Slot Filling and Intent Prediction (N18-2)

Challenge:	Neuropsychological examinations are an important screening tool for the presence of cognitive conditions such as Alzheimer's, Parkinson's and spinal-cord injuries.
Approach:	They propose to use audio recordings to determine the cognitive health of 92 subjects from audio that was diarized using an automatic speech recognition system trained on TED talks and on structured language used by testers and subjects.
Outcome:	The proposed method can determine the cognitive health of 92 subjects from audio that was diarized using an automatic speech recognition system trained on TED talks and on the structured language used by testers and subjects.

Copied to clipboard

Chih-Wen Goo, Guang Gao, Yun-Kai Hsu, Chih-Li Huo, Tsung-Chieh Chen, Keng-Wei Hsu, Yun-Nung Chen

Semantic Parsing

Challenge:	Existing approaches for slot filling and intent detection have independent attention weights, but they suffer from error propagation due to their independent models.
Approach:	They propose a slot gate that focuses on learning the relationship between intent and slot attention vectors to obtain better semantic frame results by the global optimization.
Outcome:	The proposed model significantly improves sentence-level semantic frame accuracy with 4.2% and 1.9% relative improvement compared to the attentional model on benchmark ATIS and Snips datasets respectively.

An Evaluation of Image-Based Verb Prediction Models against Human Eye-Tracking Data (N18-2)

Copied to clipboard

Spandana Gella, Frank Keller

Visual Data in NLP

Challenge:	Recent research in language and vision has developed models for predicting and disambiguating verbs from images.
Approach:	They propose a verb prediction model and visual sense disambiguation model for verbs . they ask whether the image regions a model identifies as salient correlate with human intuitions about visual verbs.
Outcome:	The proposed model can predict verbs from images, but it is unclear to what extent it captures human intuitions about visual verbs.

Learning to Color from Language (N18-2)

Copied to clipboard

Varun Manjunatha, Mohit Iyyer, Jordan Boyd-Graber, Larry Davis

Punny Captions: Witty Wordplay in Image Descriptions (N18-2)

Challenge:	Automatic colorization is the process of adding color to greyscale images.
Approach:	They propose two different architectures for language-conditioned colorization that produce more accurate and plausible colorizations than a language-agnostic version.
Outcome:	The proposed architectures produce more accurate and plausible colorizations than a language-agnostic version.

Copied to clipboard

Arjun Chandrasekaran, Devi Parikh, Mohit Bansal

The Emergence of Semantics in Neural Network Representations of Visual Information (N18-2)

Challenge:	Developing computational models that can produce contextually witty image descriptions is challenging because of the large corpus of sentences that are not available for large scale corpora.
Approach:	They propose to use linguistic wordplay, specifically puns, to generate witty image descriptions from large corpus of sentences or encode them via an encoder-decoder neural network architecture.
Outcome:	The proposed models perform better than baseline models using human data and show that they are slightly wittier than human-written witty descriptions.

Copied to clipboard

Dhanush Dharmaretnam, Alona Fyshe

Visual Data in NLP

Challenge:	Convolutional neural networks learn about semantics through corpora, but they must be shared . a recent study shows that concepts exist independently of language .
Approach:	They employ techniques previously used to detect semantic representations in the human brain to detect representations of CNNs.
Outcome:	The proposed techniques could be used to combat adversarial attacks on CNNs, the authors say .

Visual Referring Expression Recognition: What Do Systems Actually Learn? (N18-2)

Copied to clipboard

Volkan Cirik, Louis-Philippe Morency, Taylor Berg-Kirkpatrick

Visual Data in NLP

Challenge:	Existing systems for referring expression recognition ignore linguistic structure, instead relying on shallow correlations introduced by unintended biases in the data selection and annotation process.
Approach:	They propose to use a system trained on the input image without the input referring expression to achieve a precision of 71.2% in top-2 predictions.
Outcome:	The proposed model can achieve 71.2% accuracy on the input image without the input referring expression and 84.2% on the object category given the input.

Visually Guided Spatial Relation Extraction from Text (N18-2)

Copied to clipboard

Taher Rahgooy, Umar Manzoor, Parisa Kordjamshidi

Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video Captioning (N18-2)

Challenge:	Existing studies show that spatial relations can be extracted with a good accuracy, but spatial relation extraction is still challenging.
Approach:	They propose to use visual modality to fill the information gap in the text modality and resolve spatial semantic ambiguities.
Outcome:	The proposed model fills the information gap in the text modality and resolves spatial semantic ambiguities.

Copied to clipboard

Xin Wang, Yuan-Fang Wang, William Yang Wang