ACL.2021 - Findings

#1 Explainable Inference Over Grounding-Abstract Chains for Science Questions

#2 LV-BERT: Exploiting Layer Variety for BERT

#3 Few-Shot Event Detection with Prototypical Amortized Conditional Random Field

#4 LUX (Linguistic aspects Under eXamination): Discourse Analysis for Automatic Fake News Classification

#5 Diagnosing Transformers in Task-Oriented Semantic Parsing

#6 Semantic Relation-aware Difference Representation Learning for Change Captioning

#7 The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification

#8 From What to Why: Improving Relation Extraction with Rationale Graph

#9 More Parameters? No Thanks!

#10 SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics

#11 Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade

#12 Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech

#13 REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training

#14 CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction

#15 Discovering Topics in Long-tailed Corpora with Causal Intervention

#16 More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods

#17 WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections

#18 CoDesc: A Large Code–Description Parallel Dataset

#19 Deep Cognitive Reasoning Network for Multi-hop Question Answering over Knowledge Graphs

#20 GoG: Relation-aware Graph-over-Graph Network for Visual Dialog

#21 Joint Optimization of Tokenization and Downstream Model

#22 How does Attention Affect the Model?

#23 Contrastive Attention for Automatic Chest X-ray Report Generation

#24 O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning

#25 Better Chinese Sentence Segmentation with Reinforcement Learning