JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/18171

Title: Leveraging Extended Chat History through Sentence Embedding in Multi-turn Dialogue toward Increasing User Engagement
Authors: Ding, Zeyu
Elibol, Armagan
Nak-Young, Chong
Keywords: Multi-turn Dialogue
Human-Robot Interaction
Issue Date: 2022-11
Publisher: Institute of Control, Robotics and Systems (ICROS)
Magazine name: 2022 22nd International Conference on Control, Automation and Systems (ICCAS)
Start page: 642
End page: 649
DOI: 10.23919/ICCAS55662.2022.10003889
Abstract: Multi-turn dialogue is the major manifestation of a conversation. Compared with single-turn dialogue, response selection is more complex as the context varies. We stress the importance of dialogue history and apply the pre-trained model BERT to assign proper weight to each utterance of a dialogue. Previous works take all the dialogue history as context to measure the matching degree of a context-response pair, causing the quadratic computational cost and truncation of longer sequences exceeding the length limitation of BERT. We propose a sentence-based method to deal with the aforementioned problems, obtaining the sentence embedding of a single unit utterance of dialogue and forming a classification token of a context-response pair. We discuss how to obtain a sentence embedding with high quality and to design the input representations in response selection. The results show that the average of the first-last layer output exhibits the best performance for obtaining a sentence representation. The proposed method, concatenating the sentence embeddings of context with the token embeddings of response candidates, is nearly on a par with the token embedding based SOTA method. Notably, the processable length of dialogue history is enlarged about ten times with a low computational cost, potentially reducing chatbot response time and inspiring user engagement.
Rights: This is the author's version of the work. Copyright (C)ICROS. 2022 22nd International Conference on Control, Automation and Systems (ICCAS 2022), 2022, pp.642-649. DOI:10.23919/ICCAS55662.2022.10003889. Personal use of this material is permitted.This material is posted here with permission of Institute of Control, Robotics and Systems (ICROS).
URI: http://hdl.handle.net/10119/18171
Material Type: author
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
MultTurn_ICCAS2022.pdf600KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.


Contact : Library Information Section, Japan Advanced Institute of Science and Technology