Vocabulary matters: a simple yet effective approach to paragraph-level question generation

Vishwajeet Kumar, Manish Joshi, Ganesh Ramakrishnan , Yuan-Fang Li

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Question generation (QG) has recently attracted considerable attention. Most of the current neural models take as input only one or two sentences, and perform poorly when multiple sentences or complete paragraphs are given as input. However, in real-world scenarios it is very important to be able to generate high-quality questions from complete paragraphs. In this paper, we present a simple yet effective technique for answer-aware question generation from paragraphs. We augment a basic sequence-to-sequence QG model with dynamic, paragraph-specific dictionary and copy attention that is persistent across the corpus, without requiring features generated by sophisticated NLP pipelines or handcrafted rules. Our evaluation on SQuAD shows that our model significantly outperforms current state-of-the-art systems in question generation from paragraphs in both automatic and human evaluation. We achieve a 6-point improvement over the best system on BLEU-4, from 16.38 to 22.62.
Original languageEnglish
Title of host publicationThe 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, Proceedings of the Conference
EditorsKevin Knight, Hua Wu
Place of PublicationStroudsburg PA USA
PublisherAssociation for Computational Linguistics (ACL)
Pages781-785
Number of pages5
ISBN (Electronic)9781952148910
Publication statusPublished - 2020
EventConference of the Asia-Pacific Chapter of the
Association for Computational Linguistics and
the International Joint Conference on
Natural Language Processing 2020
- Online, Suzhou, China
Duration: 4 Dec 20207 Dec 2020
Conference number: 1st
https://aclanthology.org/volumes/2020.aacl-main/ (Proceedings)
http://aacl2020.org (Website)

Conference

ConferenceConference of the Asia-Pacific Chapter of the
Association for Computational Linguistics and
the International Joint Conference on
Natural Language Processing 2020
Abbreviated titleAACL-IJCNLP 2020
CountryChina
CitySuzhou
Period4/12/207/12/20
Internet address

Cite this