Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Adaptive Transformers for Learning Multimodal Representations (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing approaches for learning visiolinguistic representations with transformers are over-parametrized and require extensive training. |
| Approach: | They propose to extend attention spans, sparse, and structured dropout methods to learn more about how the network perceives the complexity of input sequences. |
| Outcome: | The proposed approaches improve on language semantics and visiolinguistic representations, but are often over-parametrized and require large amounts of computation. |
Story-level Text Style Transfer: A Proposal (2020.acl-srw)
Copied to clipboard
| Challenge: | Text style transfer is a task that aims to change the style of input text to the target style while preserving the content to some extent. |
| Approach: | They propose to use story-level text style transfer to generate stories that preserve plot . they propose to employ BERT-based method, Story Realization method, and Graph-based methods . |
| Outcome: | The proposed method preserves the plot of the input story while exhibiting a strong target style. |
Unsupervised Paraphasia Classification in Aphasic Speech (2020.acl-srw)
Copied to clipboard
| Challenge: | Aphasia is a speech and language disorder which results from brain damage resulting in word retrieval deficit (anomia) . supervised learning methods cant be properly utilized as there is no aphasic speech data. |
| Approach: | They propose an unsupervised method which can be implemented without the need for labeled paraphasia data. |
| Outcome: | The proposed method outperforms supervised learning methods and transfer learning approaches for English without labeled paraphasia data. |
HGCN4MeSH: Hybrid Graph Convolution Network for MeSH Indexing (2020.acl-srw)
Copied to clipboard
| Challenge: | Recent deep learning methods for MeSH indexing fail to capture complex correlations between terms. |
| Approach: | They propose a model to learn the relationship between MeSH terms using Graph Convolution Network (GCN) they use two biGRUs to learn embedding representations of abstract and title of MeSH index text . |
| Outcome: | The proposed model is competitive with the state-of-the-art models on two datasets. |
Grammatical Error Correction Using Pseudo Learner Corpus Considering Learner’s Error Tendency (2020.acl-srw)
Copied to clipboard
| Challenge: | Recent studies have focused on improving the performance of grammatical error correction (GEC) tasks using pseudo data. |
| Approach: | They propose to extract sentences similar to those written by language learners and generate pseudo errors by considering error types that learners often make. |
| Outcome: | The proposed model significantly improves the performance of the Russian GEC task compared with other models using pseudo data. |
Research on Task Discovery for Transfer Learning in Deep Neural Networks (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing deep neural network based machine learning models suffer from overfitting and are sensitive to noise and examples that are not available in training data. |
| Approach: | They propose to use a novel multi-task learner to implement deep neural network based transfer learning models that can be used to improve generalization. |
| Outcome: | The proposed model performs better on two NLP tasks and is more efficient on other areas of machine learning, including Bioinformatics and Computer Vision. |
RPD: A Distance Function Between Word Embeddings (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing word embeddings are poorly understood, but little is known about how they differ between different sets of word embeds. |
| Approach: | They propose a metric called Relative Pairwise Inner Product Distance to quantify the distance between different word embeddings. |
| Outcome: | The proposed metric measures the distance between different sets of embeddings and investigates the influence of different training processes and corpora. |
Reflection-based Word Attribute Transfer (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing word embeddings represent analogic relations to change attributes, such as gender, such that king is male. |
| Approach: | They propose a method for word attribute transfer based on reflection mappings without such an analogy operation. |
| Outcome: | The proposed method can transfer attributes of the given words without changing the words that do not have the target attributes. |
Topic Balancing with Additive Regularization of Topic Models (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for topic modelling on unbalanced data contain topics in various proportions and documents of the relatively small theme become distributed all over the larger topics instead of being grouped into one topic. |
| Approach: | They propose a new regularizer for topic models on unbalanced data collections . they make sure this regularizer increases the quality of topic models, trained on unstructured data . |
| Outcome: | The proposed method improves the quality of topic models trained on unbalanced datasets. |
Combining Subword Representations into Word-level Representations in the Transformer Architecture (2020.acl-srw)
Copied to clipboard
| Challenge: | Currently dominant approaches use word-level tokens, but this increases the length of the sequences and makes it difficult to profit from word-based information. |
| Approach: | They propose to combine subword-level representations into word-level ones in the first layers of the encoder, reducing the effective length of the sequences in the following layers. |
| Outcome: | The proposed model maintains translation quality with no extra word-level information . it is superior to the current dominant method for incorporating word- level source language information a priori . |
Zero-shot North Korean to English Neural Machine Translation by Character Tokenization and Phoneme Decomposition (2020.acl-srw)
Copied to clipboard
| Challenge: | a limited number of North Korean to English translation models have been developed . a zero-shot approach is proposed to train a neural machine translation model using South Korean data . |
| Approach: | They propose a method to tokenize South Korean input sentences and decompose them into phonemes. |
| Outcome: | The proposed method improves the BLEU scores by +1.01 points compared with the baseline . the proposed method can learn North Korean to English translation and improve the linguistic accuracy. |
Media Bias, the Social Sciences, and NLP: Automating Frame Analyses to Identify Bias by Word Choice and Labeling (2020.acl-srw)
Copied to clipboard
| Challenge: | slanted news coverage can have negative effects on individuals and society . a system that helps readers to become aware of the differences in media coverage caused by bias is being developed. |
| Approach: | They propose to use natural language processing and deep learning to identify instances of WCL bias and estimate the frames they induce. |
| Outcome: | The proposed system can identify instances of WCL bias and estimate the frames they induce. |
SCAR: Sentence Compression using Autoencoders for Reconstruction (2020.acl-srw)
Copied to clipboard
| Challenge: | Sentence compression is the task of shortening a sentence while retaining its meaning. |
| Approach: | They propose to use a supervised deep learning framework to shorten sentences while retaining their meaning by a compressor and reconstructor. |
| Outcome: | The proposed model achieves higher ROUGE scores on benchmark datasets than the existing state-of-the-art methods and baselines. |
Feature Difference Makes Sense: A medical image captioning model exploiting feature difference and tag information (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing methods for medical image captioning are limited and lack diversity . current methods do not generalize well when applied to unfamiliar images . |
| Approach: | They propose a feature difference and tag information combined long short-term memory model for chest x-ray report generation. |
| Outcome: | The proposed model outperforms existing models in chest x-ray report generation. |
Multi-Task Neural Model for Agglutinative Language Translation (2020.acl-srw)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has been gaining popularity in high-resource translation tasks, but struggles in low-ressource and morphologically-rich scenarios. |
| Approach: | They propose a multi-task neural model that jointly learns to perform bi-directional translation and agglutinative language stemming. |
| Outcome: | The proposed model can significantly improve translation performance on agglutinative languages by using a small amount of monolingual data. |
Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing explanation methods produce invalid or syntactically incorrect data, neglecting the improved abilities of recent NLP models. |
| Approach: | They propose an explanation method that combines occlusion and language models to sample valid and syntactically correct replacements with high likelihood, given the context of the original input. |
| Outcome: | The proposed method can sample valid and syntactically correct replacements with high likelihood, given the context of the original input. |
Non-Topical Coherence in Social Talk: A Call for Dialogue Model Enrichment (2020.acl-srw)
Copied to clipboard
| Challenge: | Current models of dialogue focus on utterances within a topically coherent discourse segment, not on social conversations . a pilot annotation study of NTUs is a first step towards a model capable of rationalizing conversational coherence in social talk. |
| Approach: | They conduct a pilot annotation study of social dialogues as a first step towards a Bayesian game-theoretic model . they first annotate content-based coherence relations that are not available in Disco-SPICE . |
| Outcome: | The proposed model can rationalize conversational coherence in social talk, the authors say . the study focuses on the natural occurring social dialogues in the Disco-SPICE corpus . |
Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models (2020.acl-srw)
Copied to clipboard
| Challenge: | Several analysis methods have been shown to be limited and are not well understood . thesis aims to understand distributional semantic representations based on linguistic data . |
| Approach: | They propose a framework for investigating the information encoded in distributional semantic models . they combine observations made on corpora with insights obtained from data manipulation experiments . |
| Outcome: | The proposed framework pairs observations made on corpora with insights obtained from data manipulation experiments. |
A Simple and Effective Dependency Parser for Telugu (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing dependency parsers for Telugu use hand-crafted features based on linguistic information like part-of-speech and morphology which are expensive to annotate. |
| Approach: | They propose to replace linguistic feature templates with a minimal feature function for Telugu . they train a BERT model on the Telugus Wikipedia data and use contextual vector representations to train the parser. |
| Outcome: | The proposed parser achieves state-of-the-art for Telugu using contextual vector representations . the proposed model trains on the Telugus Wikipedia data and trains with a greedy transition based approach . |
Pointwise Paraphrase Appraisal is Potentially Problematic (2020.acl-srw)
Copied to clipboard
| Challenge: | prevailing methods for paraphrase identification models are binary classification problems . current methods do not provide consistent and robust performance on unseen samples and real world problems. |
| Approach: | They propose to use binary classification to evaluate paraphrase identification models . they propose to improve methods for fine-tuning BERT models by pairing two sentences as one sequence . |
| Outcome: | The proposed methods may fail on simple tasks like identifying pairs with two identical sentences. |
Efficient Neural Machine Translation for Low-Resource Languages via Exploiting Related Languages (2020.acl-srw)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) is a rapidly advancing MT paradigm that can be used to improve machine translation for many languages. |
| Approach: | They propose a technique called Unified Transliteration and Subword Segmentation to leverage language similarity while exploiting parallel data from related languages. |
| Outcome: | The proposed approach improves translation accuracy by 5 BLEU points over the standard Transformer-based NMT models. |
Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder (2020.acl-srw)
Copied to clipboard
| Challenge: | EE is a key requirement for machine learning in many domains, e.g., legal, medical, finance. |
| Approach: | They propose an interpretable approach for event extraction that jointly trains a classifier and a rule decoder for event processing. |
| Outcome: | The proposed approach can be used for semi-supervised learning and its performance improves when trained on automatically-labeled data generated by a rule-based system. |
Crossing the Line: Where do Demographic Variables Fit into Humor Detection? (2020.acl-srw)
Copied to clipboard
| Challenge: | Recent shared tasks for humor classification have struggled with two issues: the data comprises a highly constrained genre of humor which does not broadly represent humor, or the data is so indiscriminate that the inter-annotator agreement on its humor content is drastically low. |
| Approach: | They propose adding demographic information about the humor annotators in order to bin ratings more sensibly and adding an ‘offensive’ label to distinguish between different generations, in terms of humor. |
| Outcome: | The proposed system could be adapted to more nuanced tasks and improve performance on downstream tasks, such as content moderation. |
Effectively Aligning and Filtering Parallel Corpora under Sparse Data Conditions (2020.acl-srw)
Copied to clipboard
| Challenge: | Parallel corpora are key to developing good machine translation systems, but abundant parallel data is hard to come by for languages with a low number of speakers. |
| Approach: | They propose an unsupervised alignment method that can handle rich morphology by removing incorrect translations and segments containing extraneous data. |
| Outcome: | The proposed method maximizes the number of correctly translated segments in a corpus and minimises noise by removing incorrect translations and segments containing extraneous data. |
Understanding Points of Correspondence between Sentences for Abstractive Summarization (2020.acl-srw)
Copied to clipboard
| Challenge: | Using points of correspondence, fusion systems are difficult for abstractive summarizers because of their complexity. |
| Approach: | They propose to model points of correspondence between disparate sentences by combining documents, source and fusion sentences, and human annotations of points of correspondance between sentences. |
| Outcome: | The proposed model bridges the gap between coreference resolution and summarization by using human annotations of points of correspondence between sentences. |
uBLEU: Uncertainty-Aware Automatic Evaluation Method for Open-Domain Dialogue Systems (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing evaluation metrics for text generation tasks do not consider uncertain responses without writing additional reference responses by hand. |
| Approach: | They propose a human-aided, uncertainty-aware evaluation method for open-domain dialogue systems, BLEU. |
| Outcome: | The proposed method is comparable to existing methods on Twitter and improves state-of-the-art evaluation method RUBER. |
To compress or not to compress? A Finite-State approach to Nen verbal morphology (2020.acl-srw)
Copied to clipboard
| Challenge: | a transitive verb takes up to 1,740 unique features and is highly complex, with a morphological complexity of 80.3% . a finite-state approach has been used to build morphology and phonology resources for Nen, an underresourced language in Papua New Guinea. |
| Approach: | They propose to use Finite-State methods to build a verbal morphological parser for an under-resourced Papuan language, Nen. |
| Outcome: | The proposed model is half the size of the full decomposed model, while the 'Chunking' model is under half the scale of the decomposer, with an overall accuracy of 80.3%. |
AraDIC: Arabic Document Classification Using Image-Based Character Embeddings and Class-Balanced Loss (2020.acl-srw)
Copied to clipboard
| Challenge: | a novel image-based character embedding framework is used for text classification in Arabic . classical methods require morphological analysis, word segmentation, and hand-crafted feature engineering. |
| Approach: | They propose a novel end-to-end Arabic document classification framework, Arabic document image-based classifier, inspired by image-basic character embeddings. |
| Outcome: | The proposed framework improves on modern standard Arabic, colloquial Arabic, and Classical Arabic. |
Embeddings of Label Components for Sequence Labeling: A Case Study of Fine-grained Named Entity Recognition (2020.acl-srw)
Copied to clipboard
| Challenge: | In general, the labels used in sequence labeling consist of different types of elements. |
| Approach: | They propose to integrate label component information as embeddings into sequence labeling models. |
| Outcome: | The proposed method improves on English and Japanese fine-grained named entity recognition on low-frequency labels. |
Building a Japanese Typo Dataset from Wikipedia’s Revision History (2020.acl-srw)
Copied to clipboard
| Challenge: | Typographical errors (typos) also occur in user generated content (UGC). |
| Approach: | They extract over half a million Japanese typo–correction pairs from Wikipedia’s revision history and combine character-based extraction rules, morphological analyzers to guess readings, and various filtering methods to address these challenges. |
| Outcome: | The proposed dataset extracts over half a million typo–correction pairs from Wikipedia’s revision history. |
Preventing Critical Scoring Errors in Short Answer Scoring with Confidence Estimation (2020.acl-srw)
Copied to clipboard
Hiroaki Funayama, Shota Sasaki, Yuichiroh Matsubayashi, Tomoya Mizumoto, Jun Suzuki, Masato Mita, Kentaro Inui
| Challenge: | Recent Short Answer Scoring systems use Quadratic Weighted Kappa (QWK) but it is unsatisfactory when measuring their effectiveness in actual usage. |
| Approach: | They propose a task formulation of Short Answer Scoring (SAS) that matches actual usage and extracts as many scoring predictions that are not critical scoring errors (CSEs). |
| Outcome: | The proposed system predicts scores with zero critical scoring errors (CSEs) for 50% of test data at maximum by filtering out low-reliability predictions on the basis of a certain confidence estimation. |
How much complexity does an RNN architecture need to learn syntax-sensitive dependencies? (2020.acl-srw)
Copied to clipboard
| Challenge: | Long-term memory (LSTM) networks are capable of encapsulating long-range dependencies . but simple recurrent networks (SRNs) have been less successful at capturing long-term dependencies and loci of grammatical errors in an unsupervised setting. |
| Approach: | They propose a new architecture that incorporates the decaying nature of neuronal activations and models the excitatory and inhibitory connections in a population of neurons. |
| Outcome: | The proposed architecture shows competitive performance relative to LSTMs on subject-verb agreement, sentence grammaticality, and language modeling tasks. |
Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. |
| Approach: | They propose an unsupervised method to derive multilingual sentence embeddings using monolingual data. |
| Outcome: | The proposed method improves on two parallel corpus mining tasks and for other languages. |
Logical Inferences with Comparatives and Generalized Quantifiers (2020.acl-srw)
Copied to clipboard
| Challenge: | Comparative constructions pose a challenge in Natural Language Inference (NLI) Comparatives interact with quantifiers, numerals, and lexical antonyms, but a logical inference system for comparatives has not been developed for the task. |
| Approach: | They propose a compositional semantics system that maps comparative constructions to semantic representations via combinatory categorial grammar parsers and integrates it with an automated theorem proving system. |
| Outcome: | The proposed system outperforms previous logic-based systems and deep learning models on three NLI datasets. |
Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources (2020.acl-srw)
Copied to clipboard
| Challenge: | In this paper, we present an effective method for semantic specialization of word vector representations. |
| Approach: | They propose a method for semantic specialization of word vector representations using BabelNet. |
| Outcome: | The proposed method improves on word similarity and dialog state tracking tasks. |
Pre-training via Leveraging Assisting Languages for Neural Machine Translation (2020.acl-srw)
Copied to clipboard
| Challenge: | Sequence-to-sequence (S2S) pre-training with large monolingual data is not always available for the languages of interest (LOI). |
| Approach: | They propose to use monolingual corpora of other languages to complement the scarce monolingual LOI by script mapping (Chinese to Japanese) . Using only Chinese and French monolinguals, they improve Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios. |
| Outcome: | The proposed approach improves Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios. |
Checkpoint Reranking: An Approach to Select Better Hypothesis for Neural Machine Translation Systems (2020.acl-srw)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) has produced excellent results in the field of machine translation due to generation of high-quality translations for different language pairs. |
| Approach: | They propose a method of re-ranking the outputs of Neural Machine Translation systems by focusing on the decoder's ability to generate distinct tokens and without the use of any language model or data. |
| Outcome: | The proposed method achieves translation improvement up to +0.16 BLEU points over baseline. |
Cross-Lingual Disaster-related Multi-label Tweet Classification with Manifold Mixup (2020.acl-srw)
Copied to clipboard
| Challenge: | Towards this goal, many studies have focused on disaster-related tweet classification. |
| Approach: | They compile a multilingual dataset for multi-label classification of disaster-related tweets . they show that their model generalizes to unseen disasters in the test set . |
| Outcome: | The proposed model generalizes to unseen disasters and improves with Manifold Mixup. |
Inducing Grammar from Long Short-Term Memory Networks by Shapley Decomposition (2020.acl-srw)
Copied to clipboard
| Challenge: | a recent study shows that modern neural networks understand sentences implicitly by inducing recursive structures. |
| Approach: | They propose to explicitly induce grammar by tracing the computational process of a long short-term memory network. |
| Outcome: | The proposed model can explicitly induce grammar without external knowledge . tracing the computational process of a long short-term memory network is shown to be effective . |
Exploring the Role of Context to Distinguish Rhetorical and Information-Seeking Questions (2020.acl-srw)
Copied to clipboard
| Challenge: | Social media posts often contain questions, but many of them are rhetorical and do not seek information. |
| Approach: | They propose a dataset containing questions in tweets paired with their prior tweets to provide context . they find that prior tweet and topic features can improve performance on this task . |
| Outcome: | The proposed dataset compares questions in tweets with their prior tweets to provide context . it shows that prior tweet and topic features can improve performance on this task . |
Compositional Generalization by Factorizing Alignment and Translation (2020.acl-srw)
Copied to clipboard
| Challenge: | a crucial property underlying the expressive power of human language is its systematicity. |
| Approach: | They propose to make an analogous separation between alignment and translation in neural machine translation to capture compositional structure. |
| Outcome: | The proposed architecture outperforms existing neural networks on a compositional generalization task without supervision. |
#NotAWhore! A Computational Linguistic Perspective of Rape Culture and Victimization on Social Media (2020.acl-srw)
Copied to clipboard
| Challenge: | Recent surge in online forums and movements supporting sexual assault survivors has led to the emergence of a ‘virtual bubble’ where survivors can recount their stories. |
| Approach: | They propose a transfer-learning based method to identify victim blaming language on Twitter and a single step transfer-based classification method to classify it. |
| Outcome: | The proposed method is compared with various deep learning and machine learning models on a manually annotated domain-specific dataset. |