mlsanityData to 7 Oct 2026

Learning to Paraphrase for Question Answering

arXiv 1708.06022 ↗First posted 20 Aug 2017cs.CLcited by 46

Not on the map. Why?

Abstract (arXiv)

Question answering (QA) systems are sensitive to the many different ways natural language expresses the same information need. In this paper we turn to paraphrases as a means of capturing this knowledge and present a general framework which learns felicitous paraphrases for various QA tasks. Our method is trained end-to-end using question-answer pairs as a supervision signal. A question and its paraphrases serve as input to a neural scoring model which assigns higher weights to linguistic expressions most likely to yield correct answers. We evaluate our approach on QA over Freebase and answer sentence selection. Experimental results on three datasets show that our framework consistently improves performance, achieving competitive results despite the use of simple QA models.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2019: 1; 2020: 0; 2021: 16; 2022: 11; 2023: 10; 2024: 4; 2025: 4.

46 papers.

Sort:

By area:

  1. 2022Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environmentscited by 57
  2. 2022ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answeringcited by 48
  3. 2021Knowing More About Questions Can Help: Improving Calibration in Question Answeringcited by 47
  4. 2021MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NERcited by 42
  5. 2021Learning to Synthesize Data for Semantic Parsingcited by 41
  6. 2021Why Machine Reading Comprehension Models Learn Shortcuts?cited by 40
  7. 2022On the Evaluation Metrics for Paraphrase Generationcited by 32
  8. 2021Focus Attention: Promoting Faithfulness and Diversity in Summarizationcited by 30
  9. 2021ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generationcited by 28
  10. 2021NoiseQA: Challenge Set Evaluation for User-Centric Question Answeringcited by 25
  11. 2021Factorising Meaning and Form for Intent-Preserving Paraphrasingcited by 22
  12. 2022Hierarchical Sketch Induction for Paraphrase Generationcited by 21
34 more
  1. 2021Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphscited by 18
  2. 2021Modelling Latent Translations for Cross-Lingual Transfercited by 16
  3. 2022BanglaParaphrase: A High-Quality Bangla Paraphrase Datasetcited by 15
  4. 2021From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decodingcited by 14
  5. 2023Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Modelscited by 14
  6. 2021ConRPG: Paraphrase Generation using Contexts as Regularizercited by 13
  7. 2023Paraphrase Detection: Human vs. Machine Contentcited by 12
  8. 2025Enrich and Detect: Video Temporal Grounding with Multimodal LLMscited by 12
  9. 2019An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generationcited by 11
  10. 2023GDA: Generative Data Augmentation Techniques for Relation Extraction Taskscited by 10
  11. 2021Data Augmentation for Mental Health Classification on Social Mediacited by 7
  12. 2023Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generationcited by 7
  13. 2022Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Codingcited by 6
  14. 2022ParaCotta: Synthetic Multilingual Paraphrase Corpora from the Most Diverse Translation Sample Paircited by 6
  15. 2021Privacy Policy Question Answering Assistant: A Query-Guided Extractive Summarization Approachcited by 5
  16. 2022Data Augmentation for Biomedical Factoid Question Answeringcited by 5
  17. 2023Smart Word Suggestions for Writing Assistancecited by 4
  18. 2025Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILEcited by 4
  19. 2021Learning to Selectively Learn for Weakly-supervised Paraphrase Generationcited by 3
  20. 2022A General Contextualized Rewriting Framework for Text Summarizationcited by 3
  21. 2023Data Distribution Bottlenecks in Grounding Language Models to Knowledge Basescited by 3
  22. 2022Multi-Figurative Language Generationcited by 2
  23. 2023Semantic-aware Contrastive Learning for More Accurate Semantic Parsingcited by 2
  24. 2024Learning to Adapt to Low-Resource Paraphrase Generationcited by 2
  25. 2022Investigating the use of Paraphrase Generation for Question Reformulation in the FRANK QA systemcited by 1
  26. 2023Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generationcited by 1
  27. 2023On the Robustness of Question Rewriting Systems to Questions of Varying Hardnesscited by 1
  28. 2023Semantic Parsing for Question Answering over Knowledge Graphscited by 1
  29. 2024Task-Oriented Paraphrase Analyticscited by 1
  30. 2025A Large-Scale Benchmark for Vietnamese Sentence Paraphrasescited by 1
  31. 2025Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generationcited by 1
  32. 2021Paraphrase Generation as Unsupervised Machine Translationcited by 0
  33. 2024Action Controlled Paraphrasingcited by 0
  34. 2024EzSQL: An SQL intermediate representation for improving SQL-to-text Generationcited by 0