• Home
  • Search
  • Improving Unsupervised Question Answering via Summarization-Informed Question Generation
  • Cite Icon33
  • https://doi.org/10.18653/v1/2021.emnlp-main.340Copy DOI Icon

Improving Unsupervised Question Answering via Summarization-Informed Question Generation

  • Jan 1, 2021
  • Chenyang Lyu +5 more
Show More
  • Abstract
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Question Generation (QG) is the task of generating a plausible question for a given \\textlesspassage, answer\\textgreater pair. Template-based QG uses linguistically-informed heuristics to transform declarative sentences into interrogatives, whereas supervised QG uses existing Question Answering (QA) datasets to train a system to generate a question given a passage and an answer. A disadvantage of the heuristic approach is that the generated questions are heavily tied to their declarative counterparts. A disadvantage of the supervised approach is that they are heavily tied to the domain/language of the QA dataset used as training data. In order to overcome these shortcomings, we propose a distantly-supervised QG method which uses questions generated heuristically from summaries as a source of training data for a QG system. We make use of freely available news summary data, transforming declarative summary sentences into appropriate questions using heuristics informed by dependency parsing, named entity recognition and semantic role labeling. The resulting questions are then combined with the original news articles to train an end-to-end neural QG model. We extrinsically evaluate our approach using unsupervised QA: our QG model is used to generate synthetic QA pairs for training a QA model. Experimental results show that, trained with only 20k English Wikipedia-based synthetic QA pairs, the QA model substantially outperforms previous unsupervised models on three in-domain datasets (SQuAD1.1, Natural Questions, TriviaQA) and three out-of-domain datasets (NewsQA, BioASQ, DuoRC), demonstrating the transferability of the approach.

Loading PDF

Similar Papers
  • Research Article
  • Citations41

Joint Learning of Question Answering and Question Generation

  • May 01, 2020
  • IEEE Transactions on Knowledge and Data Engineering
  • Yibo Sun +11
  • Book Chapter
  • Citations6

How Question Generation Can Help Question Answering over Knowledge Base

  • Jan 01, 2019
  • Sen Hu +2
  • Dissertation

Automatic question generation from natural language texts

  • Jan 01, 2022
  • Zhen Cao
  • PDF
  • Conference Article
  • Citations7

Can Question Generation Debias Question Answering Models? A Case Study on Question–Context Lexical Overlap

  • Jan 01, 2021
  • Kazutoshi Shinoda +2
  • Book Chapter
  • Citations8

Exploring NLP and Information Extraction to Jointly Address Question Generation and Answering

  • Jan 01, 2020
  • Artificial Intelligence Applications and Innovations
  • Pedro Azevedo +4
  • Video Transcripts

Exploring NLP and Information Extraction to jointly address Question Generation and Answering

  • Jun 08, 2020
  • Underline Science Inc.
  • Bernardo Leite
  • Conference Article
  • Citations9

Unified Question Generation with Continual Lifelong Learning

  • Apr 25, 2022
  • Wei Yuan +5
  • Video Transcripts

NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset

  • Oct 23, 2021
  • Underline Science Inc.
  • Jing Jiang +6
  • PDF
  • Conference Article
  • Citations16

NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset

  • Jan 01, 2021
  • Qiyuan Zhang +6
  • Conference Article

A Benchmark Suite of Japanese Natural Questions

  • Jan 01, 2024
  • Takuya Uematsu +3
  • Book Chapter

Triple-Joint Modeling for Question Generation Using Cross-Task Autoencoder

  • Jan 01, 2019
  • Hongling Wang +5
  • Conference Article
  • Citations17

CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering

  • Dec 09, 2021
  • Xiang Yue +4
  • Research Article
  • Citations10

Semantic Question Generation Using Artificial Immunity

  • Jan 08, 2015
  • International Journal of Modern Education and Computer Science
  • Ibrahim E Fattoh +2
  • Video Transcripts

Cooperative Self-training of Machine Reading Comprehension

  • Jun 27, 2022
  • Underline Science Inc.
  • Hongyin Luo
  • Research Article
  • Citations13

Unanswerable Question Correction in Question Answering over Personal Knowledge Base

  • May 18, 2021
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • An-Zi Yen +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.