Download pdf
Survey of Context-Sensitive Processing on Dialogue Generation Model
- 1 BEIJING NORMAL UNIVERSITY ·HONG KONG BAPTIST UNIVERSITY UNITED INTERNATIONAL COLLEGE
- 2 Queen Mary University of Hainan, Beijing University of Posts and Telecommunications, LingShui, 100876, China
* Author to whom correspondence should be addressed.
Abstract
In recent years, dialogue generation models have emerged as a prominent area of research, as a crucial role in the domain of natural language processing, garner significant attention from the academic community. Existing dialogue generation models predominantly emphasize human-computer interaction, however, various context-sensitive issues should not be overlooked inherent to the process. Consequently, this paper aims to summarize and categorize these context-sensitive processing issues. Firstly, based on extant literature, an overview of the current landscape of dialogue generation models is provided. Secondly, the definition of "sensitive" is clarified, and relevant scholarly works are briefly reviewed following the definition. Thirdly, previous methods addressing context-sensitive processing within dialogue generation models are directly categorized and their specific methodologies are briefly analyzed regarding this issue. Finally, pertinent research gaps and limitations are identified while future directions for research in dialogue generation models are proposed.
Keywords
Human-machine dialogue, Machine learning, Dialogue generation model, Sensitive Content Processing
[1]. WANG Chunyu, MA Zhiqiang, DU Baoxiang, JIA Wenchao, WANG Hongbin, BAO Caijilahu. Survey of Research on End-to-End Emotional Dialogue Generation[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(2): 280-295.
[2]. Yin, Z., Zhen, L., Tingting, L., Yuanyi, W., Cuijuan, L., & Yanjie, C. (2021). Survey of Affective- Based Dialogue System.
[3]. Gieselmann, P., & Ostendorf, M. (2007, September). Problem-sensitive response generation in human-robot Dialogs. In Proceedings of the 8th SIGDial Workshop on Discourse and Dialogue (pp. 219-222).
[4]. Xue, H., Liang, Y., Mu, B., Zhang, S., Chen, Q., & Xie, L. (2023). E-chat: Emotion-sensitive Spoken Dialogue System with Large Language Models. arXiv preprint arXiv:2401.00475.
[5]. Lubis, N., Sakti, S., Yoshino, K., & Nakamura, S. (2018, April). Eliciting positive emotion through affect-sensitive dialogue response generation: A neural network approach. In Proceedings of the AAAI conference on artificial intelligence (Vol. 32,No. 1).
[6]. Povedano Álvarez, D., Sandoval Orozco,A. L., García-Miguel, J. P., & García Villalba, L. J. (2023). Learning strategies for sensitive content detection. Electronics, 12(11), 2496.
[7]. Jia,Q., Tang, H., & Zhu, K.Q. (2023). Reducing Sensitivity on Speaker Names for Text Generation from Dialogues. ArXiv, abs/2305.13833
[8]. Ma, Zhiqiang; Du, Baoxiang; Shen, Ji; Wang, Chunyu; Yang, Rui. A Sentimental and Context- Sensitive Model for the Seq2Seq- Based Dialogue Generation. Elektrotehniski Vestnik; Ljubljana Vol. 87, Iss. 3, (2020): 127-134.
[9]. Sordoni, A., Galley, M., Auli, M., Brockett, C., Ji, Y., Mitchell, M., Nie, J., Gao, J., & Dolan, W.B. (2015). A Neural Network Approach to Context-Sensitive Generation of Conversational Responses. North American Chapter of the Association for Computational Linguistics.
[10]. Ling, Y., Cai, F., Hu, X., Liu, J., Chen, W., & Chen, H. (2021). Context-Controlled Topic-Aware Neural Response Generation for Open-Domain Dialog Systems. Inf. Process. Manag., 58, 102392.
[11]. Babakov, N., Logacheva, V., Kozlova, O., Semenov, N., & Panchenko, A. (2021). Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation. arXiv preprint arXiv:2103.05345.
[12]. Parker, J. (n.d.). How does ChatGPT handle offensive or inappropriate content? James Parker. Retrieved[2024.9.12],from https://www.jamesparker.dev/how-does-chatgpt-handle-offensive-or- inappropriate-content
[13]. Chang, J.P., & Danescu-Niculescu-Mizil, C. (2019). Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop. Conference on Empirical Methods in Natural Language Processing.
[14]. PRENDINGER H, ISHIZUKA M. The empathic companion:a character- based interface that addresses users affective states[J]. Applied Artificial Intelligence, 2005, 19(3/4): 267-285.
Cite this article
Zhang,Q.;Lei,Z. (2025). Survey of Context-Sensitive Processing on Dialogue Generation Model. Applied and Computational Engineering,131,72-77.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 2nd International Conference on Machine Learning and Automation
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).