Abstract
In recent years, there has been a growing interest in dialogue systems as spoken agents and communication robots become available for practical use. Much research has been conducted on non-task oriented dialogues, in which the goal is for the dialog system to interact naturally with a person. However, at present, it cannot be said that the system and people are sufficiently able to have a natural dialogue.
Therefore, this study focuses on question generation and aims to develop natural dialogue between the system and people by generating questions that take into account the relevance of the dialogue.
Here, the topic of an utterance is extracted, and related words are obtained on the basis of information associated with the extracted topic and their literal co-occurrence. Interrogative word is selected with the utterance information considering the context, and a question is generated using the acquired related word and interrogative word.
The experimental results show the effectiveness of the proposed method in generating contextualized question.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Koiso, H., et al.: Toward construction of a large-scale corpus of conversational Japanese: on methodology of recording naturally occurring conversations. Trans. Jpn. Soc. Artif. Intell. 5, 37–42 (2015). (in Japanese)
Yoshino, K., Suzuki, Y., Nakamura, S.: Information navigation system with discovering user interests. In: Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pp. 356–359. Association for Computational Linguistic (2017)
Li, J., Galley, M., Brockett, C., Gao, J., Dolan, B.: A diversity-promoting objective function for neural conversation models. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 110–119, San Diego, California (2016)
Katayama, T., Otsuka, A., Mitsuda, K., Saitou, K., Tomita, J.: Question generation to deepen your talk. In: 32nd Annual Conference of the Japanese Society for Artificial Intelligence, 4G103–4G103, pp. 1–4 (2018). (in Japanese)
Vinyals, O., Quoc, V.L.: A neural conversational model. In arXiv preprint arXiv:1506.05869 (2015)
Horiuchi, S., Higashinaka, R.: Response generation for generating certain questions in chat-oriented dialogue systems. In: The 35th Annual Conference of the Japanese Society for Artificial Intelligence, p. 2Yin5-02, pp. 1–4 (2021). (in Japanese)
Xing, C., et al.: Topic aware neural response generation. In: Proceedings of AAAI, pp. 3351–3357 (2017)
Serban, I.V., et al.: Generating factoid questions with recurrent neural networks: the 30M factoid question-answer corpus. In: Association for Computational Linguistics, pp. 588–598 (2016)
Pan, B., Li, H., Yao, Z., Cai, D., Sun, H.: Reinforced dynamic reasoning for conversational question generation. In: Association for Computational Linguistics, pp. 2114–2124 (2019)
Roller, S., et al.: Recipes for building an open-domain chatbot. In: Association for Computational Linguistics, pp. 300–325 (2021)
Teraoka, T., Yamashita, T.: Construction of associative vocabulary learning system for Japanese learners. In: Proceedings of the 34th Pacific Asia Conference on Language, Information and Computation, pp. 294–301 (2020)
Okamoto, J., Ishizaki, S.: Construction of associative concept dictionary with distance information, and comparison with electronic concept dictionary. J. Nat. Lang. Proc. 8(4), 37–54 (2001). (in Japanese)
Liu, C., Hwa, R.: Heuristically informed unsupervised idiom usage recognition. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 1723–1731 (2018)
Funato, H., Teraoka, T.: Disambiguation of Japanese idiomatic expressions using bias in occurrence of verbs. In: International Conference on Technologies and Applications of Artificial Intelligence, pp. 114–118 (TAAI) (2020)
Komatani, H., Okada, S., Nishimoto, H., Araki, M., Nakano, M.: Multimodal dialogue data collection and analysis of annotation disagreement. In: International Workshop on Spoken Dialogue System Technology, vol. 714 (IWSDS) (2019)
Fujimura, I., Chiba, S., Ohso, M.: Lexical and grammatical features of spoken and written Japanese in contrast: exploring a lexical profiling approach to comparing spoken and written corpora. In: Proceedings of the VIIth GSCP International Conference. Speech and Corpora, pp. 393–398 (2012)
Mikolov, T, Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In arXiv preprint arXiv:1301.3781 (2013)
Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long and Short Papers), pp. 4171–4186 (2019)
Acknowledgement
This work was supported by JSPS KAKENHI Grant Numbers JP18K12434, JP18K11514, and JP22K00646.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chino, A., Teraoka, T. (2023). Relevance-Aware Question Generation in Non-task-Oriented Dialogue Systems. In: Chen, J.Y.C., Fragomeni, G. (eds) Virtual, Augmented and Mixed Reality. HCII 2023. Lecture Notes in Computer Science, vol 14027. Springer, Cham. https://doi.org/10.1007/978-3-031-35634-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-35634-6_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35633-9
Online ISBN: 978-3-031-35634-6
eBook Packages: Computer ScienceComputer Science (R0)