EACL 2021

683 papers
The 2021 edition of the EACL conference presented 313 papers, with a strong emphasis on model robustness, factual consistency, and multilingualism. Research directions included mitigating positional bias in long document processing and improving factual faithfulness in abstractive summarization. Multilingual studies focused on language-agnostic retrieval, internal English pivoting in large language models, and addressing linguistic inequality within the field. The proceedings also highlighted specialized applications in scientific NLP, including the development of the TDMSci corpus for entity tagging and the ParaSCI dataset for paraphrase generation. Methodological trends involved iterative reasoning for multi-hop tasks, syntactically controlled data augmentation, and the use of span-prediction for emotion classification. Efficiency and interpretability were addressed through techniques such as early exiting for BERT models and quantifying token influence via systematic perturbation. Prolific authors contributing to these themes included Ernie Chang, Vera Demberg, Timothy Baldwin, and Danushka Bollegala.

Top Research Directions

Research directions most represented by EACL 2021 papers.

Mitigating Data Scarcity in Low Resource Language Processing 43
Why Transformers Struggle with Code Mixed Social Media Text 40
Adapting Natural Language Processing to Dialectal Diversity 28
Computational Detection of Prosocial Online Discourse 21
Multilingual Transformers for Code Mixed Text 18
The Performance Advantage of Localized Language Pretraining 18
Shared Representation Learning via Simultaneous Multi-Task Training 17
Zero-Shot Cross-Lingual Transfer in Multilingual Language Models 16
Modeling Semantic Inversion in Sarcasm Detection 15
Statistical Term Weighting for Text Vectorization 14
Script Normalization for Multilingual and Code Mixed Text 12
Discriminating Between Closely Related Languages and Dialects 11
TF-IDF Feature Extraction with Traditional Machine Learning Classifiers 10
Offensive Language Detection in Code-Mixed Dravidian Languages 10
Addressing Class Imbalance in Text Classification 10

Top Authors

AuthorPapers
Anders Søgaard4
Hinrich Schuetze4
Timothy Baldwin4
William Yang Wang4
Asli Celikyilmaz3
Danushka Bollegala3
Gholamreza Haffari3
Hiroya Takamura3
Pontus Stenetorp3
Ryan Cotterell3
Trevor Cohn3
Vera Demberg3
Abhilasha Ravichander2
Akiko Aizawa2
Alexander Panchenko2
Andrew McCallum2
An Yan2
Artem Shelmanov2
Carolyn Rose2
Dan Roth2

Impactful Papers

Papers from EACL 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Can You Distinguish Truthful from Fake Reviews? User Analysis and Assistance Tool for Fake Review Detection
Capturing Covertly Toxic Speech via Crowdsourcing
CDˆ2CR: Co-reference resolution across documents and domains
CDA: a Cost Efficient Content-based Multilingual Web Document Aligner
CFILT IIT Bombay@LT-EDI-EACL2021: Hope Speech Detection for Equality, Diversity, and Inclusion using Multilingual Representation fromTransformers
ChainCQG: Flow-Aware Conversational Question Generation
Challenges in Annotating and Parsing Spoken, Code-switched, Frisian-Dutch Data
Challenges in Automated Debiasing for Toxic Language Detection
Challenges in Designing Games with a Purpose for Abusive Language Annotation
Challenges in Designing Natural Language Interfaces for Complex Visual Models
Changing the Mind of Transformers for Topically-Controllable Language Generation
Character Set Construction for Chinese Language Learning
ChEMU-Ref: A Corpus for Modeling Anaphora Resolution in the Chemical Domain
CHOLAN: A Modular Approach for Neural Entity Linking on Wikipedia and Wikidata
Civil Rephrases Of Toxic Texts With Self-Supervised Transformers
Classification of mental illnesses on social media using RoBERTa
CLiMP: A Benchmark for Chinese Language Model Evaluation
Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration
Cluster Analysis of Online Mental Health Discourse using Topic-Infused Deep Contextualized Representations
Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa - A Large Romanian Sentiment Data Set
COCO-EX: A Tool for Linking Concepts from Texts to ConceptNet
Codewithzichao@DravidianLangTech-EACL2021: Exploring Multilingual Transformers for Offensive Language Identification on Code Mixing Text
Codewithzichao@DravidianLangTech-EACL2021: Exploring Multimodal Transformers for Meme Classification in Tamil Language
Co-evolution of language and agents in referential games
Cognition-aware Cognate Detection
Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings
Combining Context-Free and Contextualized Representations for Arabic Sarcasm Detection and Sentiment Identification
Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification
Comment Section Personalization: Algorithmic, Interface, and Interaction Design
Communicative-Function-Based Sentence Classification for Construction of an Academic Formulaic Expression Database
Comparing Approaches to Dravidian Language Identification
Comparing Similarity of Words Based on Psychosemantic Experiment and RuWordNet
Comparing the Performance of CNNs and Shallow Models for Language Identification
Complementary Evidence Identification in Open-Domain Question Answering
Complex Question Answering on knowledge graphs using machine translation and multi-task learning
Conceptual Grounding Constraints for Truly Robust Biomedical Name Representations
Conditional Adversarial Networks for Multi-Domain Text Classification
Content-based Models of Quotation
Context-aware Neural Machine Translation with Mini-batch Embedding
Context-sensitive evaluation of automatic speech recognition: considering user experience & language variation
Continuous Learning in Neural Machine Translation using Bilingual Dictionaries
Contrastive Multi-document Question Generation
Conversational Agent for Daily Living Assessment Coaching Demo
Conversational Question Answering over Knowledge Graphs with Transformer and Graph Attention Networks
Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational Modeling
Country-level Arabic Dialect Identification using RNNs with and without Linguistic Features
Country-level Arabic Dialect Identification Using Small Datasets with Integrated Machine Learning Techniques and Deep Learning Models
CovRelex: A COVID-19 Retrieval System with Relation Extraction
Creating Domain Dependent Turkish WordNet and SentiNet
Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO

« prev Page 3/14 next »