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/10119/18787

Title: Persona-based Dialogue Generation with Sentence Embedding for Prolonged Human-Robot Communication
Authors: Yue, Chen
Elibol, Armagan
Chong, Nak Young
Keywords: Human-Robot Interaction
Dialogue generation
Issue Date: 2023-10
Publisher: Institute of Control, Robotics and Systems (ICROS)
Magazine name: 2023 23rd International Conference on Control, Automation and Systems (ICCAS)
Start page: 1657
End page: 1664
DOI: 10.23919/ICCAS59377.2023.10316939
Abstract: It is one of the most fundamental and challenging problems for current dialogue generation systems to maintain the consistency of dialogue logic during the conversation. Also, the lack of an open-source annotated personabased dialogue dataset may lead to insufficient training volume for the model. Besides, the computational time and computational memory required by the attention mechanism have become drastically large. In order to overcome these problems, in this work, we propose a vertical-structure model based on the BERT model with the sentence embedding method. The model generates a raw response based on the sentence embeddings of context and persona and finally revises the raw response according to the persona. Moreover, an understanding task is designed for the BERT decoder to have a better revision ability. Considering the difference between the generation and the understanding models, three kinds of input methods are designed for each part of the model. Comparative and experimental results are presented using publicly available datasets.
Rights: This is the author's version of the work. Copyright (C) ICROS. 2023 23rd International Conference on Control, Automation and Systems (ICCAS 2023), 2023, pp. 1657-1664. DOI: 10.23919/ICCAS59377.2023.10316939. 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/10119/18787
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
N-CHONG-I-1122-1.pdf878KbAdobe 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