Generation

Pretrained Language Model for Text Generation: A Survey IJCAI 2021 Pretrain-Finetune Based Training of Task-Oriented Dialogue Systems in a Real-World Setting NAACL 2021 Pre-training Methods for Neural Machine Translation ACL 2021 Pre-training Universal Language Representation ACL 2021 PRIDE: Predicting Relationships in Conversations EMNLP 2021 Probing Across Time: What Does RoBERTa Know and When? EMNLP 2021 Probing Commonsense Explanation in Dialogue Response Generation EMNLP 2021 Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness EMNLP 2021 Progressive Generation of Long Text with Pretrained Language Models NAACL 2021 Progressive Open-Domain Response Generation with Multiple Controllable Attributes IJCAI 2021 Project Debater APIs: Decomposing the AI Grand Challenge EMNLP 2021 ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation ACL 2021 Proxy Indicators for the Quality of Open-domain Dialogues EMNLP 2021 Putting Words in BERT’s Mouth: Navigating Contextualized Vector Spaces with Pseudowords EMNLP 2021 Q2: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering EMNLP 2021 QACE: Asking Questions to Evaluate an Image Caption EMNLP 2021 QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization NAACL 2021 QuestEval: Summarization Asks for Fact-based Evaluation EMNLP 2021 Question Generation for Adaptive Education ACL 2021 R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling ACL 2021 RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems ACL 2021 RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging EMNLP 2021 Rationales for Sequential Predictions EMNLP 2021 Rational LAMOL: A Rationale-based Lifelong Learning Framework ACL 2021 Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation ACL 2021