Data Augmentation for Question Answering Using Transformer-based VAE with Negative Sampling

Wataru Kano, Koichi Takeuchi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a method to improve the accuracy of extracting appropriate question-answer pairs using generated questions with negative sampling. The base question-answering system that extracts similar questions for input queries is constructed on a Sentence-BERT model to carry out pairwised-ranking between questions of question-answer data and the input queries. The key issue of improving the question answering system is how we can prepare the enough size and variety of training examples. The Sentence-BERT model is trained on positive and negative pairs of extended questions generated by a Transformer-based Variational Autoencoder as well as human. Experimental results show that performance of retrieving appropriate questions for input queries is improved when the Sentence-BERT model is trained with the negative samples that are most similar to the positive examples.

Original languageEnglish
Title of host publicationProceedings - 2022 12th International Congress on Advanced Applied Informatics, IIAI-AAI 2022
EditorsTokuro Matsuo, Kunihiko Takamatsu, Yuichi Ono
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages467-470
Number of pages4
ISBN (Electronic)9781665497558
DOIs
Publication statusPublished - 2022
Event12th International Congress on Advanced Applied Informatics, IIAI-AAI 2022 - Kanazawa, Japan
Duration: Jul 2 2022Jul 7 2022

Publication series

NameProceedings - 2022 12th International Congress on Advanced Applied Informatics, IIAI-AAI 2022

Conference

Conference12th International Congress on Advanced Applied Informatics, IIAI-AAI 2022
Country/TerritoryJapan
CityKanazawa
Period7/2/227/7/22

Keywords

  • Negative sampling
  • Question answering system
  • Sentence-BERT
  • Variational Autoencoder

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Decision Sciences (miscellaneous)

Fingerprint

Dive into the research topics of 'Data Augmentation for Question Answering Using Transformer-based VAE with Negative Sampling'. Together they form a unique fingerprint.

Cite this