ACL.2021 - Findings

[P] [K] Explainable Inference Over Grounding-Abstract Chains for Science Questions

[P] [K] LV-BERT: Exploiting Layer Variety for BERT

[P] [K] Few-Shot Event Detection with Prototypical Amortized Conditional Random Field

[P] [K] LUX (Linguistic aspects Under eXamination): Discourse Analysis for Automatic Fake News Classification

[P] [K] Diagnosing Transformers in Task-Oriented Semantic Parsing

[P] [K] Semantic Relation-aware Difference Representation Learning for Change Captioning

[P] [K] The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification

[P] [K] From What to Why: Improving Relation Extraction with Rationale Graph

[P] [K] More Parameters? No Thanks!

[P] [K] SyGNS: A Systematic Generalization Testbed Based on Natural Language Semantics

[P] [K] Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade

[P] [K] Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech

[P] [K] REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training

[P] [K] CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction

[P] [K] Discovering Topics in Long-tailed Corpora with Causal Intervention

[P] [K] More than just Frequency? Demasking Unsupervised Hypernymy Prediction Methods

[P] [K] WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections

[P] [K] CoDesc: A Large Code–Description Parallel Dataset

[P] [K] Deep Cognitive Reasoning Network for Multi-hop Question Answering over Knowledge Graphs

[P] [K] GoG: Relation-aware Graph-over-Graph Network for Visual Dialog

[P] [K] Joint Optimization of Tokenization and Downstream Model

[P] [K] How does Attention Affect the Model?

[P] [K] Contrastive Attention for Automatic Chest X-ray Report Generation

[P] [K] O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning

[P] [K] Better Chinese Sentence Segmentation with Reinforcement Learning