Presentation 2022-07-09
Retrieval of Similar Questions from QAbot Data based on Transformer Language Model
Zihao Chen, Hisashi Handa, Kimiaki Shirahama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It has recently become possible to collect a large amount of question-answer pairs that arose in certain educational courses. However, one of the biggest difficulties to utilize such data is the lack of a retrieval system that helps a student efficiently find answers to his/her own question. This paper presents our system that takes advantage of a transformer language model which keeps breaking the state-of-the-art in various natural language processing tasks. In particular, our system uses Sentence-BERT to extract a useful feature of a question, so that questions semantically similar to the user’s one can be accurately identified through their feature matching. In addition, an important prerequisite for objective performance evaluation is a large-scale dataset containing many question-answer pairs. For this, a bot is developed on Slack to collect 1142 question-answer pairs that are individually annotated with the relevance to each of 20 queries. The experimental results on this dataset validate the effectiveness of our system based on Sentence-BERT.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Question answering / Information retrieval / Transformer / Sentence-BERT / QAbot
Paper # ET2022-9
Date of Issue 2022-07-02 (ET)

Conference Information
Committee ET
Conference Date 2022/7/9(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Data Accumulation, Analysis and Practice Application of Learning History Data, etc.
Chair Kenji Watanabe(Hiroshimai Univ.)
Vice Chair Hisayoshi Kunimune(Chiba Inst. of Tech.)
Secretary Hisayoshi Kunimune(Mejiro Univ.)
Assistant Kazuaki Yoshihara(Kinki Univ.) / Toru Kano(Tokyo University of Science)

Paper Information
Registration To Technical Committee on Educational Technology
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Retrieval of Similar Questions from QAbot Data based on Transformer Language Model
Sub Title (in English)
Keyword(1) Question answering
Keyword(2) Information retrieval
Keyword(3) Transformer
Keyword(4) Sentence-BERT
Keyword(5) QAbot
1st Author's Name Zihao Chen
1st Author's Affiliation Kindai University(Kindai Univ.)
2nd Author's Name Hisashi Handa
2nd Author's Affiliation Kindai University(Kindai Univ.)
3rd Author's Name Kimiaki Shirahama
3rd Author's Affiliation Kindai University(Kindai Univ.)
Date 2022-07-09
Paper # ET2022-9
Volume (vol) vol.122
Number (no) ET-102
Page pp.pp.5-11(ET),
#Pages 7
Date of Issue 2022-07-02 (ET)