Learning to Paraphrase for Question Answering
arXiv:1708.06022
Abstract
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.
EMNLP 2017
References in corpus (2)
Cited by in corpus (15)
- Unsupervised Paraphrase Generation using Pre-trained Language Models
- Paraphrase Generation with Deep Reinforcement Learning
- An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation
- Natural language understanding for task oriented dialog in the biomedical domain in a low resources context
- Data Augmentation for Neural Online Chat Response Selection
- ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation
- Large-scale Cloze Test Dataset Created by Teachers
- SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases
- Question Generation from SQL Queries Improves Neural Semantic Parsing
- Learning an Executable Neural Semantic Parser
- Paraphrase Generation as Unsupervised Machine Translation
- Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System
- ReDecode Framework for Iterative Improvement in Paraphrase Generation
- Concurrent Learning of Semantic Relations
- ODSQA: Open-domain Spoken Question Answering Dataset