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
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?
Don't Let Discourse Confine Your Model: Sequence Perturbations for Improved Event Language Models
Don't Miss the Labels: Label-semantic Augmented Meta-Learner for Few-Shot Text Classification
Don’t Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data
DoT: An efficient Double Transformer for NLP tasks with tables
Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis
Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering
Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking
Duluth at SemEval-2021 Task 11: Applying DeBERTa to Contributing Sentence Selection and Dependency Parsing for Entity Extraction
DuluthNLP at SemEval-2021 Task 7: Fine-Tuning RoBERTa Model for Humor Detection and Offense Rating
DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications
DUTH at SemEval-2021 Task 7: Is Conventional Machine Learning for Humorous and Offensive Tasks enough in 2021?
DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue
DynaEval: Unifying Turn and Dialogue Level Evaluation
Dynamic and Multi-Channel Graph Convolutional Networks for Aspect-Based Sentiment Analysis
Dynamic Connected Networks for Chinese Spelling Check
Dynamic Contextualized Word Embeddings
Dynamic Facet Selection by Maximizing Graded Relevance
Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering
DynaSent: A Dynamic Benchmark for Sentiment Analysis
DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation
E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning
EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets
Early Detection of Sexual Predators in Chats
EBERT: Efficient BERT Inference with Dynamic Structured Pruning
Ecco: An Open Source Library for the Explainability of Transformer Language Models
Edit Distance Based Curriculum Learning for Paraphrase Generation
Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation
Effective Attention Sheds Light On Interpretability
Effective Batching for Recurrent Neural Network Grammars
Efficient Passage Retrieval with Hashing for Open-domain Question Answering
Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations
Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification
Element Intervention for Open Relation Extraction
EmailSum: Abstractive Email Thread Summarization
Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event
Embracing Ambiguity: Shifting the Training Target of NLI Models
eMLM: A New Pre-training Objective for Emotion Related Tasks
Empathy and Hope: Resource Transfer to Model Inter-country Social Media Dynamics
Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling
Employing Argumentation Knowledge Graphs for Neural Argument Generation
Empowering Language Understanding with Counterfactual Reasoning
Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators
Encouraging Neural Machine Translation to Satisfy Terminology Constraints
EndTimes at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with BERT and Ensembles
End-to-End AMR Corefencence Resolution
End-to-End AMR Coreference Resolution
End-to-End Construction of NLP Knowledge Graph
End-to-End Lexically Constrained Machine Translation for Morphologically Rich Languages
End-to-end mBERT based Seq2seq Enhanced Dependency Parser with Linguistic Typology knowledge

« prev Page 10/34 next »