Entailment Relation Aware Paraphrase Generation
Not on the map. Why?
Abstract (arXiv)
We introduce a new task of entailment relation aware paraphrase generation which aims at generating a paraphrase conforming to a given entailment relation (e.g. equivalent, forward entailing, or reverse entailing) with respect to a given input. We propose a reinforcement learning-based weakly-supervised paraphrasing system, ERAP, that can be trained using existing paraphrase and natural language inference (NLI) corpora without an explicit task-specific corpus. A combination of automated and human evaluations show that ERAP generates paraphrases conforming to the specified entailment relation and are of good quality as compared to the baselines and uncontrolled paraphrasing systems. Using ERAP for augmenting training data for downstream textual entailment task improves performance over an uncontrolled paraphrasing system, and introduces fewer training artifacts, indicating the benefit of explicit control during paraphrasing.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 20 Mar 2022.
Builds on
31 of 53 references.
References · 31
- 2017Attention Is All You Needcited by 59,932
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019The Curious Case of Neural Text Degenerationcited by 2,881
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
- 2015A large annotated corpus for learning natural language inferencecited by 1,837
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
- 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 864
- 2015Generating Sentences from a Continuous Spacecited by 607
- 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 415
- 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
- 2018Hypothesis Only Baselines in Natural Language Inferencecited by 291
- 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 282
19 more
- 2018Breaking NLI Systems with Sentences that Require Simple Lexical Inferencescited by 134
- 2018CGMH: Constrained Sentence Generation by Metropolis-Hastings Samplingcited by 93
- 2020Syntactic Data Augmentation Increases Robustness to Inference Heuristicscited by 85
- 2019A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfercited by 65
- 2017Paraphrase Generation with Deep Reinforcement Learningcited by 58
- 2020Neural Syntactic Preordering for Controlled Paraphrase Generationcited by 56
- 2017A Deep Generative Framework for Paraphrase Generationcited by 54
- 2016Neural Paraphrase Generation with Stacked Residual LSTM Networkscited by 52
- 2019Controllable Paraphrase Generation with a Syntactic Exemplarcited by 44
- 2019ParaBank: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-constrained Neural Machine Translationcited by 38
- 2019Reinforcement Learning Based Text Style Transfer without Parallel Training Corpuscited by 38
- 2019Unsupervised Paraphrasing by Simulated Annealingcited by 37
- 2016Domain Control for Neural Machine Translationcited by 36
- 2019Decomposable Neural Paraphrase Generationcited by 30
- 2020Unsupervised Paraphrasing via Deep Reinforcement Learningcited by 25
- 2020On Learning Text Style Transfer with Direct Rewardscited by 24
- 2020Reinforced Rewards Framework for Text Style Transfercited by 12
- 2020Multi-Style Transfer with Discriminative Feedback on Disjoint Corpuscited by 12
- 2021Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learningcited by 10
Built on by
Citing papers per year: 2022: 2; 2023: 1.
3 papers.