EMNLP2021 generation相关论文

1. Contrastive Domain Adaptation for Question Answering using Limited Text Corpora
2. $Q^2$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering
3. A Large-Scale Dataset for Empathetic Response Generation
4. Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems
5. Structural Adapters in Pretrained Language Models for AMR-to-Text Generation
6. IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation
7. Interactive Machine Comprehension with Dynamic Knowledge Graphs
8. Time-aware Graph Neural Network for Entity Alignment between Temporal Knowledge Graphs
9. A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
10. TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph
11. More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous Knowledge
12. Document-level Entity-based Extraction as Template Generation
13. Parallel Refinements for Lexically Constrained Text Generation with BART
14. Weakly-supervised Text Classification Based on Keyword Graph
15. Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering
16. Adaptive Information Seeking for Open-Domain Question Answering
17. Few-Shot Text Generation with Natural Language Instructions
18. Distantly-Supervised Dense Retrieval Enables Open-Domain Question Answering without Evidence Annotation
19. ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models
20. Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation
21. Data-to-text Generation by Splicing Together Nearest Neighbors
22. Unsupervised Relation Extraction: A Variational Autoencoder Approach
23. Neural Natural Logic Inference for Interpretable Question Answering
24. Iterative GNN-based Decoder for Question Generation
25. EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation Learning