NEURAL APPROACHES

Uncertainty Modeling for Machine Comprehension Systems using Efficient Bayesian Neural Networks (2020.coling-industry)

Challenge:	Existing approaches to extract summarize text are based on sentences as the elementary unit, but semantic segments containing supplementary information or descriptive details are often nonessential in the generated summaries.
Approach:	They propose to exploit discourse-level segmentation as a finer-grained means to more precisely pinpoint the core content in a document.
Outcome:	The proposed method improves extractive summarization performance on CNN/Daily Mail dataset.

Copied to clipboard

Zhengyuan Liu, Pavitra Krishnaswamy, Ai Ti Aw, Nancy Chen

UZH@CRAFT-ST: a Sequence-labeling Approach to Concept Recognition (D19-57)

Challenge:	Neural approaches have improved machine comprehension tasks, but models often operate as a black-box, resulting in lower interpretability.
Approach:	They propose a hybrid approach to quantify model uncertainty using Bayesian weight approximation and boost up inference speed by 80% relative to test time.
Outcome:	The proposed approach boosts inference speed by 80% relative to the previous approach and is applied to a clinical dialogue comprehension task.

Copied to clipboard

Lenz Furrer, Joseph Cornelius, Fabio Rinaldi

string2string: A Modern Python Library for String-to-String Algorithms (2024.acl-demos)

Challenge:	CRAFT shared task 2019: concept recognition using named entity recognition and normalization . a biLSTM-based network and a transformer system were used to tackle both tasks in a single model .
Approach:	They propose two different neural approaches to concept recognition . they propose a BiLSTM-based network and a bioBERT-based system for NER and normalization .
Outcome:	The proposed systems model the task as a sequence labeling problem.

Copied to clipboard

Mirac Suzgun, Stuart Shieber, Dan Jurafsky

Neural Approaches for Natural Language Interfaces to Databases: A Survey (2020.coling-main)

Challenge:	Notable algorithms include the Smith-Waterman algorithm for pairwise local alignment, the Hirschberg algorithm for global alignment, and the Wagner-Fischer algorithm for edit distance.
Approach:	string2string is an open-source library that offers efficient algorithms for string-to-string problems.
Outcome:	string2string is an open-source library that offers efficient algorithms for string-to-string problems.

Copied to clipboard

Radu Cristian Alexandru Iacob, Florin Brad, Elena-Simona Apostol, Ciprian-Octavian Truică, Ionel Alexandru Hosu, Traian Rebedea

GAINER: Graph Machine Learning with Node-specific Radius for Classification of Short Texts and Documents (2024.eacl-long)

Challenge:	Interest in NLIDBs has resurged in the past years due to the availability of large datasets and improvements to neural sequence-to-sequence models.
Approach:	They focus on key design decisions behind current state of the art neural approaches . they highlight linking question tokens to database schema elements .
Outcome:	The proposed approaches are grouped into encoder and decoder improvements . they include better architectures for encoding the textual query taking into account the schema and improved generation of structured queries using autoregressive neural models.

Copied to clipboard

Naganand Yadati

Design Challenges in Named Entity Transliteration (C18-1)

Challenge:	Recent advances in Graph Machine Learning (GML) have led to the development of numerous models tailored for processing text for various natural language applications.
Approach:	They propose a framework called Graph mAchine learnIng with Node-spEcific Radius that is aimed at graph-based NLP.
Outcome:	The proposed framework is non-neural and novel for graph-based NLP.

Copied to clipboard

Yuval Merhav, Stephen Ash

Multilinguality

Challenge:	Named entity transliteration is an important component in many search and language understanding tasks.
Approach:	They empirically evaluate a named entity transliteration task using traditional methods . they use a stack of convolutional layers to create a neural network with a new approach .
Outcome:	The proposed system outperforms two neural approaches in the named entity transliteration task.

SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling (N18-1)

Copied to clipboard

Ana Marasović, Anette Frank

LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking (2021.acl-long)

Challenge:	Recent neural approaches do not outperform the state-of-the-art feature-based models for Opinion Role Labeling (ORL).
Approach:	They propose to use multi-task learning to improve Opinion Role Labeling by using a related task which has substantially more data.
Outcome:	The proposed model outperforms the state-of-the-art model for Opinion Role Labeling (ORL) with more data.

Copied to clipboard

Hang Jiang, Sairam Gurajada, Qiuhao Lu, Sumit Neelam, Lucian Popa, Prithviraj Sen, Yunyao Li, Alexander Gray

TONY: an open-source TOolkit for Nlp in psYchology (2026.acl-demo)

Challenge:	Existing work deals with EL in the context of longer text, such as a sentence.
Approach:	They propose a neuro-symbolic approach that uses interpretable rules based on first-order logic to achieve better performance with black-box neural approaches.
Outcome:	The proposed approach achieves better performance than heuristics-based approaches on short-text EL . it can easily blend existing rule templates with multiple types of features, and even with scores resulting from previous EL methods.

Copied to clipboard

Federico Ravenda, Sofia Irene Ravenda, Volodymyr Karpenko, Daniele Montagnani, Andrea Raballo, Antonietta Mira

Challenge:	Existing NLP tools are fragmented, closed-source, or difficult to use . a single sentence can convey emotion, social dynamics, cognitive states, and implicit attitudes .
Approach:	They propose an open-source python TOolkit for NLP in clinical psychology.
Outcome:	The TOolkit bridges traditional psycholinguistic analysis and modern NLP . it integrates interpretable lexical features with state-of-the-art lightweight transformer models . the toolkit is released under an open-source license and is evaluated through multiple MH–related datasets.

Dialo-AP: A Dependency Parsing Based Argument Parser for Dialogues (2022.coling-1)

Copied to clipboard

Sougata Saha, Souvik Das, Rohini K. Srihari

Multimodality

Challenge:	a recent work on argument mining has focused on parsing monologues, while neglecting dialogues.
Approach:	They propose an end-to-end argument parser that constructs argument graphs from dialogues . they use extensive pre-training and curriculum learning to train AM .
Outcome:	The proposed system performs all sub-tasks of AM and achieves significant improvements . it is compared to existing systems and validated through human evaluation .

AirConcierge: Generating Task-Oriented Dialogue via Efficient Large-Scale Knowledge Retrieval (2020.findings-emnlp)

Copied to clipboard

Chieh-Yang Chen, Pei-Hsin Wang, Shih-Chieh Chang, Da-Cheng Juan, Wei Wei, Jia-Yu Pan

Natural Language Interfaces

Challenge:	Existing neural task-oriented dialogue systems cannot be encoded by memory networks, such as memory networks.
Approach:	They propose an end-to-end trainable text-to SQL guided framework to learn a neural agent that interacts with KBs using the generated SQL queries.
Outcome:	The proposed method significantly improves on the AirDialogue dataset, which contains the conversations of customers booking flight tickets from the agent.

Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech (2021.findings-acl)

Copied to clipboard

Yi-Ling Chung, Serra Sinem Tekiroğlu, Marco Guerini

Event Temporal Relation Extraction with Bayesian Translational Model (2023.eacl-main)

Challenge:	Existing approaches to combat online hatred using informed textual responses - called counter narratives - produce generic/repetitive responses and lack grounded and up-to-date evidence such as facts, statistics, or examples.
Approach:	They propose to automatically generate counter narratives using an external knowledge repository to provide more informative content to fight online hatred.
Outcome:	The proposed pipeline can generate suitable and informative counter narratives in in-domain and cross-domain settings.

Copied to clipboard

Xingwei Tan, Gabriele Pergola, Yulan He

Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue (P19-1)

Challenge:	Existing methods to extract temporal relations between events lack a principled method to incorporate external knowledge.
Approach:	They propose a Bayesian-based method that models the temporal relation representations as latent variables and infers their values via Bayessian inference and translational functions.
Outcome:	The proposed method outperforms existing methods for event temporal relation extraction on three widely used datasets.

Copied to clipboard

Anusha Balakrishnan, Jinfeng Rao, Kartikeya Upasani, Michael White, Rajen Subba

Strong Baselines for Neural Semi-Supervised Learning under Domain Shift (P18-1)

Challenge:	Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems.
Approach:	They propose using tree-structured semantic representations for better discourse-level structuring and sentence-level planning and introduce a challenging dataset using this representation for the weather domain.
Outcome:	The proposed model improves discourse-level structuring and sentence-level planning on a weather domain and can be decoded to improve semantic correctness.

Copied to clipboard

Sebastian Ruder, Barbara Plank

Filling Missing Paths: Modeling Co-occurrences of Word Pairs and Dependency Paths for Recognizing Lexical Semantic Relations (N18-1)

Challenge:	Existing neural models for learning under domain shifts only evaluate on a single task, on proprietary datasets, or compare to weak baselines.
Approach:	They propose a multi-task tri-training method that reduces time and space complexity of classic bootstrapping approaches.
Outcome:	The proposed method outperforms the state-of-the-art for sentiment analysis on two benchmarks.

Copied to clipboard

Koki Washio, Tsuneaki Kato

Challenge:	Existing approaches to recognize lexical semantic relations between word pairs require that word pairs co-occur in a sentence.
Approach:	They propose to exploit lexico-syntactic paths between two target words to exploit the semantic relations between word pairs.
Outcome:	The proposed model can generalize the co-occurrences of word pairs and dependency paths and extract features capturing relational information from word pairs.

Improving Constituent Representation with Hypertree Neural Networks (2022.naacl-main)

Copied to clipboard

Hao Zhou, Gongshen Liu, Kewei Tu

Representation Learning

Challenge:	Existing methods of span representation are based on simple derivations from word representations and do not utilize compositional structures of natural language.
Approach:	They propose a hypertree neural network that is structured with constituency parse trees to improve representations of constituent spans.
Outcome:	The proposed model improves representations of constituent spans using constituency parse trees.

Dependency parsing with structure preserving embeddings (2021.eacl-main)

Copied to clipboard

Ákos Kádár, Lan Xiao, Mete Kemertas, Federico Fancellu, Allan Jepson, Afsaneh Fazly

Representation Learning

Challenge:	Modern neural approaches to dependency parsing are trained to predict a tree structure by learning a contextual representation for tokens in a sentence and a head–dependent scoring function.
Approach:	They propose to combine a contextual representation for tokens and a head–dependent scoring function to learn interpretable representations by training a parser to explicitly preserve structural properties of a tree.
Outcome:	The proposed approach yields strong tree distance preservation and parsing performance on par with a competitive graph-based parser.

Data-to-Text Generation with Style Imitation (2020.findings-emnlp)

Copied to clipboard

Shuai Lin, Wentao Wang, Zichao Yang, Xiaodan Liang, Frank F. Xu, Eric Xing, Zhiting Hu

Text Generation

Challenge:	Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles.
Approach:	They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach .
Outcome:	The proposed approach achieves stronger performance than a range of comparison methods.

End-to-End Neural Word Alignment Outperforms GIZA++ (2020.acl-main)

Copied to clipboard

Thomas Zenkel, Joern Wuebker, John DeNero

Machine Translation

Challenge:	Word alignment was once a core unsupervised learning task in natural language processing . but word alignment still plays an important role in interactive applications of neural machine translation, such as annotation transfer and lexicon injection.
Approach:	They propose to use a Transformer model to train an unsupervised word alignment model.
Outcome:	The proposed method outperforms GIZA++ on three data sets and is tightly integrated and does not affect translation quality.

DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension (P18-1)

Copied to clipboard

Amrita Saha, Rahul Aralikatte, Mitesh M. Khapra, Karthik Sankaranarayanan

Reasoning

Challenge:	DuoRC contains 186,089 unique question-answer pairs created from 7680 movie plots .
Approach:	They propose a novel dataset for Reading Comprehension that motivates new challenges for neural approaches in language understanding beyond those offered by existing RC datasets.
Outcome:	The proposed dataset motivates several new challenges for neural approaches in language understanding beyond those offered by existing RC datasets.

Aspect-based summarization of pros and cons in unstructured product reviews (C18-1)

Copied to clipboard

Florian Kunneman, Sander Wubben, Antal van den Bosch, Emiel Krahmer

Summarization

Challenge:	SynPat, a system based on syntactic phrases selected on the basis of valence scores, and a neural-network-based system trained on clusters of word-embedding encodings of similar pros and cons are compared to SynPat.
Approach:	They propose to use syntactic phrases selected on the basis of valence scores to generate pros and cons summaries.
Outcome:	The proposed systems outperform the baseline systems on held-out reviews with gold-standard pros and cons and on human annotators on relevance and completeness.

The Limitations of Limited Context for Constituency Parsing (2021.acl-long)

Copied to clipboard

Yuchen Li, Andrej Risteski

A Unified Neural Coherence Model (D19-1)

Challenge:	a language model that is syntax-aware can produce better samples, authors say . a recent study shows that neural approaches to syntax can perform unsupervised syntactic parsing .
Approach:	They propose to incorporate syntax into neural approaches in NLP to produce better samples . they find that the first time neural approaches were able to perform unsupervised syntactic parsing .
Outcome:	The proposed models can perform unsupervised syntactic parsing, but they are lagging behind . the proposed models are based on a sandbox of probabilistic context-free-grammars .

Copied to clipboard

Han Cheol Moon, Tasnim Mohiuddin, Shafiq Joty, Chi Xu

Challenge:	Existing models for coherence modeling fail on harder tasks with more realistic application scenarios.
Approach:	They propose a unified coherence model that incorporates sentence grammar, inter-sentence coherent relations, and global coherency patterns into a common neural framework.
Outcome:	The proposed model outperforms existing models on local and global discrimination tasks and outperformed existing models by a good margin.

Improving English-Arabic Transliteration with Phonemic Memories (2022.findings-emnlp)

Copied to clipboard

Yuanhe Tian, Renze Lou, Xiangyu Pang, Lianxi Wang, Shengyi Jiang, Yan Song

Challenge:	Existing neural approaches to transliterate names from English to Arabic are limited and focus on leveraging the phonemic association between English and Arabic.
Approach:	They propose a model for English-Arabic transliteration using a memory module modeling the phonemic association between English and Arabic to guide the transliterations process.
Outcome:	The proposed model improves on EANames corpus, which better represents names in the general public than linked Wikipedia entries that are always names of famous people.

Multi-task Pairwise Neural Ranking for Hashtag Segmentation (P19-1)

Copied to clipboard

Mounica Maddela, Wei Xu, Daniel Preoţiuc-Pietro

Low-Resource NLP

Challenge:	Hashtags are used to add metadata to textual utterances, but their semantic content is difficult to infer as they often contain multiple tokens joined together.
Approach:	They propose to use a dataset of 12,594 hashtags to infer hashtag semantics . they propose to frame the problem as a pairwise ranking problem between candidate segmentations .
Outcome:	The proposed methods show 24.6% error reduction in hashtag segmentation accuracy compared to the current state-of-the-art method.

Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks (2020.emnlp-main)

Copied to clipboard

Chengyue Jiang, Yinggong Zhao, Shanbo Chu, Libin Shen, Kewei Tu

deepQuest: A Framework for Neural-based Quality Estimation (C18-1)

Challenge:	Neural networks typically need large labeled data for training and are not easily interpretable.
Approach:	They propose a type of recurrent neural networks that combine neural networks and regular expression rules.
Outcome:	The proposed recurrent neural networks outperform previous neural approaches in low- and zero-shot scenarios and remain very competitive in rich-resource settings.

Copied to clipboard

Julia Ive, Frédéric Blain, Lucia Specia

Machine Translation

Challenge:	Predicting Machine Translation (MT) quality has been limited to word and sentence-level prediction.
Approach:	They propose a framework that can generalize neural QE approaches to the level of documents.
Outcome:	The proposed framework outperforms state-of-the-art approaches on document-level quality estimates and is 40 times faster to train.

Transferring Knowledge from Structure-aware Self-attention Language Model to Sequence-to-Sequence Semantic Parsing (2022.coling-1)

Copied to clipboard

Ran Ji, Jianmin Ji

Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks (2021.eacl-main)

Challenge:	Semantic parsing aims to map a natural language sentence into a machine executable formal representation.
Approach:	They propose a structure-aware self-attention language model to capture structural information of target representations and propose incorporating it into a seq2seq model.
Outcome:	The proposed model improves the baseline model on four semantic parsing and Python code generation tasks.

Copied to clipboard

Tasnim Mohiuddin, Prathyusha Jwalapuram, Xiang Lin, Shafiq Joty

Text Generation

Challenge:	Coherence models are typically evaluated only on synthetic tasks, which may not be representative of their performance in downstream applications.
Approach:	They compare models' performance on synthetic sentences with those on retrieval-based dialog.
Outcome:	The proposed models perform poorly on synthetic sentences and retrieval-based dialog tasks.

Unsupervised Chinese Word Segmentation with BERT Oriented Probing and Transformation (2022.findings-acl)

Copied to clipboard

Wei Li, Yuhan Song, Qi Su, Yanqiu Shao

Low-Resource NLP

Challenge:	Existing methods for unsupervised Chinese word segmentation exploit shallow semantic information, which can miss important context.
Approach:	They propose to take advantage of deep contextual semantic information with a self-training manner to transform it into explicit word segmentation ability.
Outcome:	The proposed approach achieves state-of-the-art F1 score on two CWS benchmark datasets.

Continual Learning for Natural Language Generation in Task-oriented Dialog Systems (2020.findings-emnlp)

Copied to clipboard

Fei Mi, Liangwei Chen, Mengjie Zhao, Minlie Huang, Boi Faltings

Dialogue Systems & Conversational Agents

Challenge:	Existing neural approaches for natural language generation are typically developed offline for specific domains.
Approach:	They propose a method to expand NLG knowledge incrementally to new domains . major challenge is catastrophic forgetting, meaning a model forgets the knowledge it has learned before .
Outcome:	The proposed method outperforms other methods by effectively mitigating catastrophic forgetting issue.

Intent Classification and Slot Filling for Privacy Policies (2021.acl-long)

Copied to clipboard

Wasi Ahmad, Jianfeng Chi, Tu Le, Thomas Norton, Yuan Tian, Kai-Wei Chang

Transparent Semantic Parsing with Universal Dependencies Using Graph Transformations (2022.coling-1)

Challenge:	Sentences written in privacy policies explain privacy practices and the constituent text spans convey further specific information.
Approach:	They propose an English corpus of 5,250 intent and 11,788 slot annotations . they propose two alternative neural approaches to model the corpus as a sequence-to-sequence learning task.
Outcome:	The proposed corpus predicts intent classification and slot filling, while the sequence tagging method outperforms slot filler by a large margin.

Copied to clipboard

Wessel Poelman, Rik van Noord, Johan Bos

ESC: Redesigning WSD with Extractive Sense Comprehension (2021.naacl-main)

Challenge:	Existing semantic parsers are based on deep learning, but rule-based approaches offer advantages . a drawback of neural semantic parses is that their output lacks explainability .
Approach:	They propose a method that maps a syntactic dependency tree to a formal meaning representation using a series of graph transformations.
Outcome:	The proposed method outperforms neural parsers in English, German, Italian and Dutch.

Copied to clipboard

Edoardo Barba, Tommaso Pasini, Roberto Navigli

ProSeqo: Projection Sequence Networks for On-Device Text Classification (D19-1)

Challenge:	Word Sense Disambiguation (WSD) is a historical NLP task aimed at linking words in contexts to discrete sense inventories.
Approach:	They propose a transformer-based neural architecture for extractive Sense Comprehension to solve a span extraction problem and a new state of the art English WSD task.
Outcome:	The proposed model outdoes all of its competitors while relying on three times fewer annotations.

Copied to clipboard

Zornitsa Kozareva, Sujith Ravi

Information Retrieval

Challenge:	ProSeqo is a novel on-device sequence model for text classification . it uses dynamic recurrent projections without the need to store or look up pre-trained embeddings.
Approach:	They propose a novel on-device sequence model for text classification using recurrent projections that uses dynamic recursion projections without the need to store or look up any pre-trained embeddings.
Outcome:	The proposed model outperforms state-of-the-art neural and on-device approaches for short and long text classification tasks while maintaining low memory footprint and high accuracy.

Validity Assessment of Legal Will Statements as Natural Language Inference (2022.findings-emnlp)

Copied to clipboard

Alice Kwak, Jacob Israelsen, Clayton Morrison, Derek Bambauer, Mihai Surdeanu

Reasoning

Challenge:	This study introduces a dataset that focuses on the validity of statements in legal wills.
Approach:	They propose a dataset that focuses on the validity of statements in legal wills.
Outcome:	The proposed model achieves 80% macro F1 and accuracy, but group accuracy is in mid 80s at best, suggesting that the models’ understanding of the task remains superficial.

Jointly Learning to Align and Translate with Transformer Models (D19-1)

Copied to clipboard

Sarthak Garg, Stephan Peitz, Udhyakumar Nallasamy, Matthias Paulik

Modeling Input Uncertainty in Neural Network Dependency Parsing (D18-1)

Challenge:	Existing word alignment models are not accurate for word alignments.
Approach:	They propose a method to train a Transformer model to produce accurate translations and alignments.
Outcome:	The proposed model outperforms GIZA++ trained models on translation and alignment tasks while maintaining translation accuracy.

Copied to clipboard

Rob van der Goot, Gertjan van Noord

Syntactic Text Processing

Challenge:	Recent advances in neural network parsers address data sparsity issues by modeling character level information and exploiting raw data in semi-supervised settings.
Approach:	They investigate whether lexical normalization provides similar functionality to lexiconal normalization . they show that a separate normalization component improves performance of a neural network parser .
Outcome:	The proposed approaches improve performance even with access to character level information and word embeddings.

SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking (P19-1)

Copied to clipboard

Hwaran Lee, Jinsik Lee, Tae-Yoon Kim

Dialogue Systems & Conversational Agents

Challenge:	Existing methods to model domain- and slot-dependent belief trackers have difficulty adding new slot-values, resulting in lack of flexibility of domain ontology configurations.
Approach:	They propose a model that captures relationships between domain-slot-types and slot-values appearing in utterances through attention mechanisms based on contextual semantic vectors.
Outcome:	The proposed model improves performance on two dialog corpora and achieves state-of-the-art accuracy.

Where are we in Named Entity Recognition from Speech? (2020.lrec-1)

Copied to clipboard

Antoine Caubrière, Sophie Rosset, Yannick Estève, Antoine Laurent, Emmanuel Morin

Speech & Audio in NLP

Challenge:	Named entity recognition is usually made through a pipeline process that consists of processing audio and applying a NER to the audio outputs.
Approach:	They propose an original 3-pass approach and explore the capability of an E2E system to do structured NER.
Outcome:	The proposed system performs better than the current pipeline approach.

Resource Constrained Dialog Policy Learning Via Differentiable Inductive Logic Programming (2020.coling-main)

Copied to clipboard

Zhenpeng Zhou, Ahmad Beirami, Paul Crook, Pararth Shah, Rajen Subba, Alborz Geramifard

ChiMST: A Chinese Medical Corpus for Word Segmentation and Medical Term Recognition (2022.lrec-1)

Challenge:	Existing methods for dialog policy learning have limited data collection and data analysis.
Approach:	They introduce dialog policy learning via differentiable inductive logic on SimDial and MultiWoZ to address resource constrained dialog policy.
Outcome:	The proposed method is 100x more data efficient than state-of-the-art neural approaches on MultiWoZ while achieving similar performance metrics.

Copied to clipboard

Yuanhe Tian, Han Qin, Fei Xia, Yan Song

Extracting Event Temporal Relations via Hyperbolic Geometry (2021.emnlp-main)

Challenge:	Chinese word segmentation and named entity recognition are important tasks in natural language processing.
Approach:	They develop a Chinese medical corpus annotated with Chinese word boundary and medical term information to address this problem.
Outcome:	The proposed corpus will be a valuable resource for Chinese word segmentation and named entity recognition research on the medical domain.

Copied to clipboard

Xingwei Tan, Gabriele Pergola, Yulan He

Representation Learning

Challenge:	Recent neural approaches to event temporal relation extraction map events to embeddings in the Euclidean space and train a classifier to detect temporal relations between event pairs.
Approach:	They propose to embed events into hyperbolic spaces to model hierarchical structures . they propose to use hyperbolical embeddings to directly infer event relations .
Outcome:	The proposed architecture is based on two approaches to encode events and their temporal relations in hyperbolic spaces.

An Improved Neural Baseline for Temporal Relation Extraction (D19-1)

Copied to clipboard

Qiang Ning, Sanjay Subramanian, Dan Roth

Exploiting Positional Bias for Query-Agnostic Generative Content in Search (2024.findings-acl)

Challenge:	Existing datasets are small and/or have low inter-annotator agreements.
Approach:	They propose a new neural system that achieves 10% absolute accuracy improvement over the previous best system.
Outcome:	The proposed system achieves 10% absolute improvement over the previous best system on two benchmark datasets.

Copied to clipboard

Andrew Parry, Sean MacAvaney, Debasis Ganguly

AD-NLP: A Benchmark for Anomaly Detection in Natural Language Processing (2023.emnlp-main)

Challenge:	Recent studies show that neural ranking models outperform lexical models in text retrieval.
Approach:	They propose to exploit transformer attention mechanism to induce exploitable defects in search models through sensitivity to token position within a sequence.
Outcome:	The proposed model can generalise beyond a single query or topic without knowledge of topicality.

Copied to clipboard

Matei Bejan, Andrei Manolache, Marius Popescu

Challenge:	Methods for Anomaly Detection in text have shown strong empirical results on ad-hoc anomaly setups that are usually made by downsampling some classes of a labeled dataset.
Approach:	They propose a unified benchmark for detecting various types of anomalies . they evaluate two strong shallow baselines and two current state-of-the-art neural approaches .
Outcome:	The proposed benchmarks provide insights into the knowledge the neural models are learning when performing the task.

REPROLANG 2020: Automatic Proficiency Scoring of Czech, English, German, Italian, and Spanish Learner Essays (2020.lrec-1)

Copied to clipboard

Andrew Caines, Paula Buttery

Information Retrieval

Challenge:	a new paper aims to reproduce the work described in Vajjala & Rama (2018) . the paper focuses on features-based and neural approaches to essay scoring in Czech, German and Italian .
Approach:	They propose to replicate the work described in Vajjala & Rama 2018, ‘Experiments with universal CEFR classification’, as part of REPROLANG 2020.
Outcome:	The proposed methods perform better than feature-based models for large text datasets, though neural network modifications do bring performance closer to the best feature-driven models.

Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence Annotation (2021.emnlp-main)

Copied to clipboard

Chen Zhao, Chenyan Xiong, Jordan Boyd-Graber, Hal Daumé III

Question Answering

Challenge:	Open-domain question answering uses evidence retrieved from large corpus to answer questions . state-of-the-art approaches require intermediate evidence annotations for training . however, such intermediate annotations are expensive and methods that rely on them cannot transfer to the more common setting .
Approach:	They propose an open-domain question answering approach that alternately finds evidence from an up-to-date model and encourages the model to learn the most likely evidence.
Outcome:	The proposed approach improves over weak retrievers on multi-hop and single-hop benchmarks without using evidence labels.

Topic Modeling: Contextual Token Embeddings Are All You Need (2024.findings-emnlp)

Copied to clipboard

Dimo Angelov, Diana Inkpen

FuzzAug: Data Augmentation by Coverage-guided Fuzzing for Neural Test Generation (2025.findings-emnlp)

Challenge:	Current neural approaches to topic modeling have not been able to solve all of the problems.
Approach:	They propose a topic modeling approach that uses document contextual token embeddings to find topics and find topic spans within documents.
Outcome:	The proposed model outperforms the current state-of-the-art models on a comprehensive set of topic model evaluation metrics.

Copied to clipboard

Yifeng He, Jicheng Wang, Yuyang Rong, Hao Chen