ACL 2021

1,666 papers

Top Research Directions

Research directions most represented by ACL 2021 papers.

Zero-Shot Cross-Lingual Transfer in Multilingual Language Models 36
Mitigating Data Scarcity in Low Resource Language Processing 32
Fine-Grained Toxicity Localization in Text 26
Constrained Sequence Decoding for Neural Labeling 23
Shared Representation Learning via Simultaneous Multi-Task Training 22
Iterative Retrieval Augmented Generation for Multi Hop Reasoning 21
Modeling Word Difficulty in Context 20
Continuous Modeling of Linguistic Complexity 19
Contextualized Word Embeddings from Pretrained Transformers 18
Mitigating Cascading Errors in Sequential Processing Pipelines 18
Joint Multilingual Training for Cross-Lingual Transfer 18
Predicting Lexical Complexity for Text Accessibility 17
Replacing Abstract Labels with Natural Language Descriptions 17
The Language Bias of English Centric Benchmarks 16
Pointer Generator Mechanisms for Grounded Text Generation 15

Top Authors

AuthorPapers
Jie Zhou22
Minlie Huang15
Yue Zhang13
Fandong Meng12
Maosong Sun12
Lei Li11
Xuanjing Huang11
Zhiyuan Liu11
Daxin Jiang9
Haifeng Wang9
Heng Ji9
Qun Liu9
Kewei Tu8
Ryan Cotterell8
Ting Liu8
Yubo Chen8
Fei Huang7
Furu Wei7
Haifeng Wang7
Ivan Vulić7

Impactful Papers

Papers from ACL 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Improving Compositional Generalization in Classification Tasks via Structure Annotations
Improving Dialog Systems for Negotiation with Personality Modeling
Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval
Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation
Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
Improving Factual Consistency of Abstractive Summarization via Question Answering
Improving Formality Style Transfer with Context-Aware Rule Injection
Improving Gradient-based Adversarial Training for Text Classification by Contrastive Learning and Auto-Encoder
Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction
Improving Model Generalization: A Chinese Named Entity Recognition Case Study
Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
Improving Paraphrase Detection with the Adversarial Paraphrasing Task
Improving Policing with Natural Language Processing
Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment
Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task
Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification
Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation
Improving Unsupervised Extractive Summarization with Facet-Aware Modeling
Improving Zero-Shot Translation by Disentangling Positional Information
IMS’ Systems for the IWSLT 2021 Low-Resource Speech Translation Task
Including Signed Languages in Natural Language Processing
Incorporating Compositionality and Morphology into End-to-End Models
Incorporating Global Information in Local Attention for Knowledge Representation Learning
Incorporating tone in the calculation of phonotactic probability
Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features
IndoCollex: A Testbed for Morphological Transformation of Indonesian Colloquial Words
IndoCollex: A Testbed for Morphological Transformation of Indonesian Word Colloquialism
Inducing Semantic Roles Without Syntax
In Factuality: Efficient Integration of Relevant Facts for Visual Question Answering
InfoSurgeon: Cross-Media Fine-grained Information Consistency Checking for Fake News Detection
Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution
INNOVATORS at SemEval-2021 Task-11: A Dependency Parsing and BERT-based model for Extracting Contribution Knowledge from Scientific Papers
Input Augmentation Improves Constrained Beam Search for Neural Machine Translation: NTT at WAT 2021
Input Representations for Parsing Discourse Representation Structures: Comparing English with Chinese
Insertion-based Tree Decoding
Inside ASCENT: Exploring a Deep Commonsense Knowledge Base and its Usage in Question Answering
Inspecting the concept knowledge graph encoded by modern language models
Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding
Integrated Directional Gradients: Feature Interaction Attribution for Neural NLP Models
Integrated Training for Sequence-to-Sequence Models Using Non-Autoregressive Transformer
Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval
IntelliCAT: Intelligent Machine Translation Post-Editing with Quality Estimation and Translation Suggestion
Intent Classification and Slot Filling for Privacy Policies
Interactive Reinforcement Learning for Table Balancing Robot
Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning
Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making
Intrinsic Bias Metrics Do Not Correlate with Application Bias
Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning
Introducing Orthogonal Constraint in Structural Probes
Investigating label suggestions for opinion mining in German Covid-19 social media

« prev Page 16/34 next »