Abstract
In order to realize character-like chatbots, it is necessary to collect dialogue data of particular characters. However, collecting such data is not an easy task. To solve this problem, we have previously proposed a method called “Role-play-based question answering” in which many users play the role of a particular character to answer questions, resulting in a large number of question-answer (QA) pairs associated with that character. In this study, we investigated how character-like dialogue could be realized by fine-tuning a pre-trained Transformer-based encoder-decoder model, which has shown its effectiveness in dialogue modelling, with the QA pairs collected via role-play-based question answering. The results of automatic and manual evaluations show that, with the fine-tuned model, it is possible to significantly outperform a retrieval-based baseline and that, with 44 K QA pairs, it is possible to achieve high naturalness and characterness scores.
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
Adiwardana D, Luong MT, So DR, Hall J, Fiedel N, Thoppilan R, Yang Z, Kulshreshtha A, Nemade G, Lu Y, Le QV (2020) Towards a human-like open-domain chatbot. arXiv:2001.09977
Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler D, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D (2020) Language models are few-shot learners. In: Proceedings of NeurIPS, pp 1877–1901
Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL, pp 4171–4186
Dinan E, Roller S, Shuster K, Fan A, Auli M, Weston J (2019) Wizard of wikipedia: knowledge-powered conversational agents. In: Proceedings of ICLR, pp 1–18
Higashinaka R, Araki M, Tsukahara H, Mizukami M (2021) Integrated taxonomy of errors in chat-oriented dialogue systems. In: Proceeding of SIGDIAL, pp 89–98
Higashinaka R, Dohsaka K, Isozaki H (2013) Using role play for collecting question-answer pairs for dialogue agents. In: Proceedings of INTERSPEECH, pp 1097–1100
Higashinaka R, Funakoshi K, Inaba M, Tsunomori Y, Takahashi T, Akama R (2021) Dialogue system live competition: identifying problems with dialogue systems through live event. In: Proceedings of IWSDS, pp 185–199
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
Higashinaka R, Mizukami M, Kawabata H, Yamaguchi E, Adachi N, Tomita J (2018) Role play-based question-answering by real users for building chatbots with consistent personalities. In: Proceedings of SIGDIAL, pp 264–272
Kodama T, Higashinaka R, Mitsuda K, Masumura R, Aono Y, Nakamura R, Adachi N, Kawabata H (2020) Generating responses that reflect meta information in user-generated question answer pairs. In: Proceedings of LREC, pp 5433–5441
Li J, Galley M, Brockett C, Gao J, Dolan B (2016) A diversity-promoting objective function for neural conversation models. In: Proceedings of NAACL-HLT, pp 110–119
Li J, Galley M, Brockett C, Spithourakis G, Gao J, Dolan B (2016) A persona-based neural conversation model. In: Proceedings of ACL, pp 994–1003
Meguro T, Higashinaka R, Minami Y, Dohsaka K (2010) Controlling listening-oriented dialogue using partially observable Markov decision processes. In: Proceedings of COLING, pp 761–769
Qian Q, Huang M, Zhao H, Xu J, Zhu X (2018) Assigning personality/profile to a chatting machine for coherent conversation generation. In: Proceedings of IJCAI, pp 4279–4285
Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ (2019) Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv:1910.10683
Rashkin H, Smith EM, Li M, Boureau YL (2019) Towards empathetic open-domain conversation models: a new benchmark and dataset. In: Proceedings of ACL, pp 5370–5381
Roller S, Dinan E, Goyal N, Ju D, Williamson M, Liu Y, Xu J, Ott M, Smith EM, Boureau YL, Weston J (2021) Recipes for building an open-domain chatbot. In: Proceedings of EACL, pp 300–325
Shazeer N, Stern M (2018) Adafactor: adaptive learning rates with sublinear memory cost. In: Proceedings of ICML, pp 4596–4604
Smith EM, Williamson M, Shuster K, Weston J, Boureau YL (2020) Can you put it all together: evaluating conversational agents’ ability to blend skills. In: Proceedings of ACL, pp 2021–2030
Sugiyama H, Narimatsu H, Mizukami M, Arimoto T, Chiba Y, Meguro T, Nakajima H (2020) Development of conversational system talking about hobby using transformer-based encoder-decoder model. In: Proceedings of special interest group on spoken language understanding and dialogue processing (in Japanese), pp 104–109
Sugiyama H, Narimatsu H, Mizukami M, Arimoto T, Chiba Y, Meguro T, Nakajima H (2021) Analysis of subjective evaluation for fine-tuning methods of transformer encoder-decoder based conversational systems. In: Proceedings of The 35th annual conference of the Japanese society for artificial intelligence (in Japanese), pp 4E1–OS–11a–03
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Proceedings of NeurIPS, pp 5998–6008
Zhang S, Dinan E, Urbanek J, Szlam A, Kiela D, Weston J (2018) Personalizing dialogue agents: i have a dog, do you have pets too? In: Proceedings of ACL, pp 2204–2213
Zhou L, Gao J, Li D, Shum HY (2020) The design and implementation of XiaoIce, an empathetic social chatbot. Comput Linguist 46(1):53–93
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mitsuda, K. et al. (2022). Fine-Tuning a Pre-trained Transformer-Based Encoder-Decoder Model with User-Generated Question-Answer Pairs to Realize Character-Like Chatbots. In: Stoyanchev, S., Ultes, S., Li, H. (eds) Conversational AI for Natural Human-Centric Interaction. Lecture Notes in Electrical Engineering, vol 943. Springer, Singapore. https://doi.org/10.1007/978-981-19-5538-9_20
Download citation
DOI: https://doi.org/10.1007/978-981-19-5538-9_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-5537-2
Online ISBN: 978-981-19-5538-9
eBook Packages: Computer ScienceComputer Science (R0)