会議発表論文

会議発表論文

text

Learning to Ask Efficiently in Dialogue: Reinforcement Learning Extensions for Stream-based Active Learning

the Special Interest Group on Discourse and Dialogue

英語

text

2025

Issei Waki, Ryu Takeda and Kazunori Komatani, Learning to Ask Efficiently in Dialogue: Reinforcement Learning Extensions for Stream-based Active Learning. the 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), 2025.

One essential function of dialogue systems is the ability to ask questions and acquire necessary information from the user through dialogue. To avoid degrading user engagement through repetitive questioning, the number of such questions should be kept low. In this study, we cast knowledge acquisition through dialogue as stream-based active learning, exemplified by the segmentation of user utterances containing novel words. In stream-based active learning, data instances are presented sequentially, and the system selects an action for each instance based on an acquisition function that determines whether to request the correct labels from the oracle (in this case, the user). To improve the efficiency of training the acquisition function via reinforcement learning, we introduce two extensions: (1) a new action that performs semi-supervised learning, and (2) a state representation that takes the remaining budget into account. Our simulation-based experiments suggested that these two extensions have the potential to improve word segmentation performance with fewer questions for the user.

This article is licensed under a Creative Commons Attribution 4.0 International License.

102765

Learning to Ask Efficiently in Dialogue: Reinforcement Learning Extensions for Stream-based Active Learning

the Special Interest Group on Discourse and Dialogue

英語

2025

https://hdl.handle.net/11094/102765