Learning to Paraphrase for Question Answering

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.

• Publication year

  2017

• Venue

  Conference on Empirical Methods in Natural Language Processing

• Publication date

  2017-08-20

• Fields of study

  Computer Science

• Identifiers
  DOI 10.18653/v1/D17-1091arXiv 1708.06022
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Universal Semantic Parsing

  2017influential reference
• Paraphrasing Revisited with Neural Machine Translation

  2017influential reference
• On Generating Characteristic-rich Question Sets for QA Evaluation

  2016cited by this paper
• Transforming Dependency Structures to Logical Forms for Semantic Parsing

  2016cited by this paper
• Key-Value Memory Networks for Directly Reading Documents

  2016influential reference
• A Decomposable Attention Model for Natural Language Inference

  2016cited by this paper
• Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing

  2016influential reference
• Improving Semantic Parsing via Answer Type Inference

  2016influential reference
• Sentence Rewriting for Semantic Parsing

  2016influential reference
• Question Answering on Freebase via Relation Extraction and Textual Evidence

  2016influential reference
• Question Answering over Freebase with Multi-Column Convolutional Neural Networks

  2015influential reference
• Neural Machine Translation of Rare Words with Subword Units

  2015cited by this paper
• Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks

  2015cited by this paper
• Imitation Learning of Agenda-based Semantic Parsers

  2015influential reference
• PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification

  2015influential reference
• Learning Natural Language Inference with LSTM

  2015cited by this paper
• Neural Variational Inference for Text Processing

  2015influential reference
• WikiQA: A Challenge Dataset for Open-Domain Question Answering

  2015cited by this paper
• Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base

  2015influential reference
• Convolutional Neural Network for Paraphrase Identification

  2015cited by this paper
• Lean Question Answering over Freebase from Scratch

  2015cited by this paper
• Improving Neural Machine Translation Models with Monolingual Data

  2015cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014influential reference
• Semantic Parsing via Paraphrasing

  2014influential reference
• Open Question Answering with Weakly Supervised Embedding Models

  2014influential reference
• GloVe: Global Vectors for Word Representation

  2014cited by this paper
• Information Extraction over Structured Data: Question Answering with Freebase

  2014influential reference
• Distributed Representations of Sentences and Documents

  2014cited by this paper
• Sequence to Sequence Learning with Neural Networks

  2014cited by this paper
• Deep Learning for Answer Sentence Selection

  2014influential reference
• Question Answering with Subgraph Embeddings

  2014influential reference
• Open question answering over curated and extracted knowledge bases

  2014influential reference
• Semantic Parsing on Freebase from Question-Answer Pairs

  2013influential reference
• Paraphrase-Driven Learning for Open Question Answering

  2013cited by this paper
• PPDB: The Paraphrase Database

  2013cited by this paper
• Dropout Improves Recurrent Neural Networks for Handwriting Recognition

  2013cited by this paper
• On the difficulty of training recurrent neural networks

  2012cited by this paper
• Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection

  2011cited by this paper
• Learning Sentential Paraphrases from Bilingual Parallel Corpora for Text-to-Text Generation

  2011cited by this paper
• 48th Annual Meeting of the Association for Computational Linguistics

  2010cited by this paper
• Natural language inference

  2009cited by this paper
• Syntactic Constraints on Paraphrases Extracted from Parallel Corpora

  2008cited by this paper
• Answering the question you wish they had asked: The impact of paraphrasing for Question Answering

  2006cited by this paper
• A Study of Translation Edit Rate with Targeted Human Annotation

  2006cited by this paper
• A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION

  2005cited by this paper
• Paraphrasing with Bilingual Parallel Corpora

  2005cited by this paper
• Statistical Phrase-Based Translation

  2003cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• Applied morphological processing of English

  2001cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• Database

  1985cited by this paper
• Natural language inference.

  1973cited by this paper

• Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE

  2025cites this paper
• Research of text paraphrase generation based on self-contrastive learning

  2025cites this paper
• Rethinking Natural Language Generation with Layer-Wise Multi-View Decoding

  2025cites this paper
• SAPG: Semantically-Aware Paraphrase Generation with AMR Graphs

  2025cites this paper
• Transforming Questions and Documents for Semantically Aligned Retrieval-Augmented Generation

  2025cites this paper
• PAM: Paraphrase AMR-Centric Evaluation Metric

  2025cites this paper
• Injecting Frame Semantics into Large Language Models via Prompt-Based Fine-Tuning

  2025cites this paper
• A Large-Scale Benchmark for Vietnamese Sentence Paraphrases

  2025cites this paper
• Data augmentation for equipment technical standard entity recognition

  2025cites this paper
• SDM-M-DID: Self-decoding model for medical de-identification

  2025cites this paper
• Enrich and Detect: Video Temporal Grounding with Multimodal LLMs

  2025cites this paper
• An aligned corpus of Spanish bibles

  2024cites this paper
• Unsupervised Disentanglement Learning Model for Exemplar-Guided Paraphrase Generation

  2024cites this paper
• Conversational Question Answering Systems: A Comprehensive Literature Review

  2024cites this paper
• Action Controlled Paraphrasing

  2024cites this paper
• Chain-of-Question: A Progressive Question Decomposition Approach for Complex Knowledge Base Question Answering

  2024influential citation
• A Large-Scale Bengali Paraphrase Generation Dataset: A Comprehensive Study of Language Models and Performance Analysis

  2024cites this paper
• Improving Quality and Domain-Relevancy of Paraphrase Generation with Graph-Based Retrieval Augmented Generation

  2024cites this paper
• EzSQL: An SQL intermediate representation for improving SQL-to-text Generation

  2024cites this paper
• Learning to Paraphrase for Alignment with LLM Preference

  2024cites this paper
• Distribution Shifts Are Bottlenecks: Extensive Evaluation for Grounding Language Models to Knowledge Bases

  2024influential citation
• Task-Oriented Paraphrase Analytics

  2024cites this paper
• Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition

  2024cites this paper
• Toward the Modular Training of Controlled Paraphrase Adapters

  2024cites this paper
• Learning to Adapt to Low-Resource Paraphrase Generation

  2024cites this paper
• Guiding Zero-Shot Paraphrase Generation with Fine-Grained Control Tokens

  2023cites this paper
• Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

  2023cites this paper
• Weak Supervision for Question and Answering Sentiment Analysis

  2023cites this paper
• Improving Vietnamese Question-Answering system with Data Augmentation and Optimization

  2023cites this paper
• Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation

  2023cites this paper
• Foundation and large language models: fundamentals, challenges, opportunities, and social impacts

  2023cites this paper
• Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation

  2023cites this paper
• Paraphrase Generation For Reading Comprehension

  2023cites this paper
• A Principled Decomposition of Pointwise Mutual Information for Intention Template Discovery

  2023cites this paper
• Enhancing Large Language Models’ Utility for Medical Question-Answering: A Patient Health Question Summarization Approach

  2023cites this paper
• Deep Latent Variable Models for Semi-supervised Paraphrase Generation

  2023cites this paper
• On the Robustness of Question Rewriting Systems to Questions of Varying Hardness

  2023cites this paper
• Data Distribution Bottlenecks in Grounding Language Models to Knowledge Bases

  2023cites this paper
• Semantic Parsing for Question Answering over Knowledge Graphs

  2023cites this paper
• Question answering models for human-machine interaction in the manufacturing industry

  2023cites this paper
• GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks

  2023cites this paper
• Graph Propagation based Data Augmentation for Named Entity Recognition

  2023cites this paper
• Paraphrase Detection: Human vs. Machine Content

  2023cites this paper
• Semantic-aware Contrastive Learning for More Accurate Semantic Parsing

  2023cites this paper
• Data augmentation using Heuristic Masked Language Modeling

  2023cites this paper
• MSQ-BioBERT: Ambiguity Resolution to Enhance BioBERT Medical Question-Answering

  2023cites this paper
• Testing Paraphrase Models on Recognising Sentence Pairs at Different Degrees of Semantic Overlap

  2023cites this paper
• Smart Word Suggestions for Writing Assistance

  2023cites this paper
• Language as a latent sequence: Deep latent variable models for semi-supervised paraphrase generation

  2023cites this paper
• RulePG: Syntactic Rule-enhanced Paraphrase Generation

  2023cites this paper
• On the Evaluation Metrics for Paraphrase Generation

  2022cites this paper
• Combining Vision and Language Representations for Patch-based Identification of Lexico-Semantic Relations

  2022cites this paper
• Zero-shot domain paraphrase with unaligned pre-trained language models

  2022cites this paper
• Multi-Figurative Language Generation

  2022cites this paper
• BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset

  2022cites this paper
• Efficient Semi-supervised Consistency Training for Natural Language Understanding

  2022cites this paper
• Detecting Frozen Phrases in Open-Domain Question Answering

  2022cites this paper
• Synthetic Data Generation for Multilingual Domain-Adaptable Question Answering Systems

  2022cites this paper
• ParaZh-22M: A Large-Scale Chinese Parabank via Machine Translation

  2022cites this paper
• Investigating the use of Paraphrase Generation for Question Reformulation in the FRANK QA system

  2022cites this paper
• You Just Want Attention

  2022cites this paper
• Data Augmentation for Biomedical Factoid Question Answering

  2022cites this paper
• Automatically Solving Elementary Science Questions: A Survey

  2022cites this paper
• ArcaneQA: Dynamic Program Induction and Contextualized Encoding for Knowledge Base Question Answering

  2022cites this paper
• Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding

  2022cites this paper
• Research on high-performance English translation based on topic model

  2022cites this paper
• Hierarchical Sketch Induction for Paraphrase Generation

  2022cites this paper
• A General Contextualized Rewriting Framework for Text Summarization

  2022cites this paper
• Natural language based analysis of SQuAD: An analytical approach for BERT

  2022cites this paper
• Paraphrase Generator for Indonesian Language: Basic Method for Generating Question on Interviewbot Engine

  2022cites this paper
• Improving data augmentation for low resource speech-to-text translation with diverse paraphrasing

  2022cites this paper
• MCPG: A Flexible Multi-Level Controllable Framework for Unsupervised Paraphrase Generation

  2022cites this paper
• ParaMac: A General Unsupervised Paraphrase Generation Framework Leveraging Semantic Constraints and Diversifying Mechanisms

  2022cites this paper
• Recent progress in leveraging deep learning methods for question answering

  2022cites this paper
• Don’t Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments

  2022cites this paper
• Pseudo Ambiguous and Clarifying Questions Based on Sentence Structures Toward Clarifying Question Answering System

  2022cites this paper
• Integrating Paraphrasing into the FRANK QA System

  2022cites this paper
• ParaCotta: Synthetic Multilingual Paraphrase Corpora from the Most Diverse Translation Sample Pair

  2022cites this paper
• Generating Factoid Questions with Question Type Enhanced Representation and Attention-based Copy Mechanism

  2022cites this paper
• Revisiting the Evaluation Metrics of Paraphrase Generation

  2022cites this paper
• Are We Evaluating Paraphrase Generation Accurately?

  2021cites this paper
• Knowledge-Guided Paraphrase Identification

  2021cites this paper
• A Well-Composed Text is Half Done! Semantic Composition Sampling for Diverse Conditional Generation

  2021cites this paper
• Paraphrase Generation: A Survey of the State of the Art

  2021cites this paper
• Ask me in your own words: paraphrasing for multitask question answering

  2021cites this paper
• Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data

  2021cites this paper
• Privacy Policy Question Answering Assistant: A Query-Guided Extractive Summarization Approach

  2021cites this paper
• Data Augmentation for Mental Health Classification on Social Media

  2021cites this paper
• ConRPG: Paraphrase Generation using Contexts as Regularizer

  2021cites this paper
• Paraphrase Generation as Unsupervised Machine Translation

  2021cites this paper
• Evaluating BERT-based Rewards for Question Generation with Reinforcement Learning

  2021influential citation
• Skeleton parsing for complex question answering over knowledge bases

  2021cites this paper
• Welcome to AI Matters 7(2)

  2021cites this paper
• MELM: Data Augmentation with Masked Entity Language Modeling for Cross-lingual NER

  2021cites this paper
• Learning to Selectively Learn for Weakly-supervised Paraphrase Generation

  2021cites this paper
• ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation

  2021cites this paper
• Reformed QANet - Optimizing the Spatial Complexity of QANet

  2021cites this paper
• Modelling Latent Translations for Cross-Lingual Transfer

  2021cites this paper
• BEAT: Considering question types for bug question answering via templates

  2021cites this paper
• Unanswerable Question Correction in Question Answering over Personal Knowledge Base

  2021cites this paper