Abstract
It is important for chat-oriented dialogue systems to be able to understand the various information from user utterances. However, no study has yet clarified the types of information that should be understood by such systems. With this purpose in mind, we collected and clustered information that humans perceive from each utterance (perceived information) in chat-oriented dialogue. We then clarified, i.e., categorized, the types of perceived information. The types were evaluated on the basis of inter-annotator agreement, which showed substantial agreement and demonstrated the validity of our categorization. To the best of our knowledge, this study is the first to clarify the types of information that a chat-oriented dialogue system should understand.
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
Dialogue-games: metacommunication structures for natural language interaction. Cogn Sci 1(4), 395–420 (1977)
Allen J (1983) Recognizing intentions from natural language utterances. MIT Press
Grice HP (1975) Logic and conversation. In: Cole P, Morgan J (eds) Syntax and semantics, vol 3: Speech acts. Academic Press, pp 41–58
Higashinaka R, Imamura K, Meguro T, Miyazaki C, Kobayashi N, Sugiyama H, Hirano T, Makino T, Matsuo Y (2014) Towards an open domain conversational system fully based on natural language processing. In: Proceedings of COLING, pp 928–939
Joshi A, Sharma V, Battacharyya P (2015) Harnessing context incongruity for sarcasm detection. In: Proceedings of ACL/IJCNLP, pp 757–762
Kim Y, Bang J, Choi J, Ryu S, Koo S, Lee GG (2014) User information extraction for personalized dialogue systems. In: Proceedings of workshop on multimodal analyses enabling artificial agents in human-machine interaction
Ma C, Prendinger H, Ishizuka M (2005) Emotion estimation and reasoning based on affective textual interaction. In: Proceedings of affective computing and intelligent interaction
Meguro T, Minami Y, Higashinaka R, Dohsaka K (2014) Learning to control listening-oriented dialogue using partially observable markov decision processe. ACM Trans Speech Lang Process 10(15):1–15
Riloff E, Quadir A, Surve P, Silva LD, Gilbert N, Huang R (2013) Sarcasm as contrast between positive sentiment and negative situation. In: Proceedings of EMNLP, pp 704–714
Takabatake Y, Morita H, Kawahara D, Kurohashi S, Higashinaka R, Matsuo Y (2015) Classification and acquisition of contradictory event pairs using crowdsourcing. In: Proceedings of the 3rd workshop on EVENTS: definition, detection, coreference, and representation, pp 99–107
Williams JD, Raux A, Ramachandran D, Black, A (2013) The dialog state tracking challenge. In: Proceedings of SIGDIAL, pp 404–413
Wong W, Cavedon L, Thangarajah J, Padgham L (2012) Flexible conversation management using a BDI agent approach. In: Proceedings of IVA, pp 464–470
Zhang C, Chai JY (2009) What do we know about conversation participants: experiments on conversation entailment. In: Proceedings of SIGDIAL, pp 206–215
Zhang C, Chai JY (2010) Towards conversation entailment: an empirical investigation. In: Proceedings of EMNLP, pp 756–766
Zhang M, Qin B, Liu T, Zheng M (2014) Triple based background knowledge ranking for document enrichment. In: Proceedings of COLING, pp 917–927
Zhang M, Qin B, Zheng M, Hirst G, Liu T (2015) Encoding distributional semantics into triple-based knowledge ranking for document enrichment. In: Proceedings of ACL/IJCNLP, pp 524–533
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Mitsuda, K., Higashinaka, R., Matsuo, Y. (2019). What Information Should a Dialogue System Understand?: Collection and Analysis of Perceived Information in Chat-Oriented Dialogue. In: Eskenazi, M., Devillers, L., Mariani, J. (eds) Advanced Social Interaction with Agents . Lecture Notes in Electrical Engineering, vol 510. Springer, Cham. https://doi.org/10.1007/978-3-319-92108-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-92108-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92107-5
Online ISBN: 978-3-319-92108-2
eBook Packages: EngineeringEngineering (R0)