Skip to main content
SpringerLink
Log in

Personalizing Retrieval-Based Dialogue Agents

  • Conference paper
  • First Online:
Speech and Computer (SPECOM 2022)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13721))

Included in the following conference series:

Abstract

The development of various kinds of interactive assistants at present is highly in demand. In this field, one critical problem is the personalization of these dialog assistants seeking to increase user loyalty and involvement in a conversation, which may be a competitive advantage for enterprises employing them. This paper presents a study of retrieve models for a personalized dialogue agent. To train models the Persona Chat and Toloka Persona Chat Rus datasets are used. The study found the most effective models among the retrieval models, learning strategies. Also, to solve one of the major limitations of the personalization of dialogue assistants—the lack of large data sets with dialogues containing person characteristics—a text data augmentation method was developed that preserves individual speech patterns and vocabulary.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Anaby-Tavor, A., Carmeli, B., Goldbraich, E., Kantor, A., Kour, G., Shlomov, S., Tepper, N., Zwerdling, N.: Not enough data? deep learning to the rescue! (2019). http://arxiv.org/abs/1911.03118

  2. Andreas, J.: Good-enough compositional data augmentation (2019). http://arxiv.org/abs/1904.09545

  3. Chalkidis, I., Androutsopoulos, I., Michos, A.: Extracting contract elements. In: Proceedings of the 16th Edition of the International Conference on Articial Intelligence and Law, pp. 19–28. ICAIL ’17, Association for Computing Machinery, New York, NY, USA (2017). https://doi.org/10.1145/3086512.3086515

  4. Coulombe, C.: Text data augmentation made simple by leveraging NLP cloud apis (2018). http://arxiv.org/abs/1812.04718

  5. 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. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https://doi.org/10.18653/v1/N19-1423, https://aclanthology.org/N19-1423

  6. Edunov, S., Ott, M., Auli, M., Grangier, D.: Understanding back-translation at scale. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 489–500. Association for Computational Linguistics, Brussels, Belgium (2018). https://doi.org/10.18653/v1/D18-1045, https://aclanthology.org/D18-1045

  7. Floridi, L., Chiriatti, M.: GPT-3: its nature, scope, limits, and consequences. Mind. Mach. 30(4), 681–694 (2020). https://doi.org/10.1007/s11023-020-09548-1

    Article  Google Scholar 

  8. Giridhara, P.K.B., Mishra, C., Venkataramana, R.K.M., Bukhari, S.S., Dengel, A.R.: A study of various text augmentation techniques for relation classification in free text. In: ICPRAM (2019)

    Google Scholar 

  9. Guo, H., Mao, Y., Zhang, R.: Augmenting data with mixup for sentence classification: an empirical study (2019). arXiv:abs/1905.08941

  10. Hancock, B., Bordes, A., Mazare, P.E., Weston, J.: Learning from dialogue after deployment: feed yourself, chatbot! pp. 3667–3684 (2019). https://doi.org/10.18653/v1/P19-1358

  11. Humeau, S., Shuster, K., Lachaux, M., Weston, J.: Real-time inference in multi-sentence tasks with deep pretrained transformers (2019). http://arxiv.org/abs/1905.01969

  12. Humeau, S., Shuster, K., Lachaux, M.A., Weston, J.: Poly-encoders: architectures and pre-training strategies for fast and accurate multi-sentence scoring. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=SkxgnnNFvH

  13. Iyyer, M., Wieting, J., Gimpel, K., Zettlemoyer, L.: Adversarial example generation with syntactically controlled paraphrase networks. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1 (Long Papers), pp. 1875–1885. Association for Computational Linguistics, New Orleans, Louisiana (2018). https://doi.org/10.18653/v1/N18-1170, https://aclanthology.org/N18-1170

  14. Kobayashi, S.: Contextual augmentation: data augmentation by words with paradigmatic relations (2018). arXiv:abs/1805.06201

  15. Kumar, V., Choudhary, A., Cho, E.: Data augmentation using pre-trained transformer models (2020). arXiv:abs/2003.02245

  16. Lin, Z., Liu, Z., Winata, G.I., Cahyawijaya, S., Madotto, A., Bang, Y., Ishii, E., Fung, P.: XPersona: evaluating multilingual personalized chatbot. In: Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI. pp. 102–112. Association for Computational Linguistics, Online (2021). https://doi.org/10.18653/v1/2021.nlp4convai-1.10, https://aclanthology.org/2021.nlp4convai-1.10

  17. Matveev, A., Makhnytkina, O., Matveev, Y., Svischev, A., Korobova, P., Rybin, A., Akulov, A.: Virtual dialogue assistant for remote exams. Mathematics 9(18) (2021). https://doi.org/10.3390/math9182229, https://www.mdpi.com/2227-7390/9/18/2229

  18. Ni, J., Young, T., Pandelea, V., Xue, F., Adiga, V., Cambria, E.: Recent advances in deep learning-based dialogue systems (2021)

    Google Scholar 

  19. Papadaki, M., Chalkidis, I., Michos, A.: Data augmentation techniques for legal text analytics (2017)

    Google Scholar 

  20. Posokhov, P., Apanasovich, K., Matveeva, A., Makhnytkina, O., Matveev, A.: Personalizing dialogue agents for Russian: retrieve and refine, vol. 2022, pp. 245–252 (2022). https://doi.org/10.23919/FRUCT54823.2022.9770895

  21. Roller, S., Dinan, E., Goyal, N., Ju, D., Williamson, M., Liu, Y., Xu, J., Ott, M., Smith, E.M., Boureau, Y.L., Weston, J.: Recipes for building an open-domain chatbot. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 300–325. Association for Computational Linguistics, Online (2021). https://doi.org/10.18653/v1/2021.eacl-main.24, https://aclanthology.org/2021.eacl-main.24

  22. Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. CoRR abs/1508.07909 (2015), http://arxiv.org/abs/1508.07909

  23. Shen, T., Lei, T., Barzilay, R., Jaakkola, T.S.: Style transfer from non-parallel text by cross-alignment (2017). arXiv:abs/1705.09655

  24. Sugiyama, H., Mizukami, M., Arimoto, T., Narimatsu, H., Chiba, Y., Nakajima, H., Meguro, T.: Empirical analysis of training strategies of transformer-based Japanese chit-chat systems (2021). arXiv:abs/2109.05217

  25. Wei, J.W., Zou, K.: EDA: easy data augmentation techniques for boosting performance on text classification tasks (2019). arXiv:abs/1901.11196

  26. Wu, X., Xia, Y., Zhu, J., Wu, L., Xie, S., Fan, Y., Qin, T.: Mixseq: a simple data augmentation method for neural machine translation, pp. 192–197 (2021). https://doi.org/10.18653/v1/2021.iwslt-1.23

  27. Yang, Z., Hu, Z., Dyer, C., Xing, E.P., Berg-Kirkpatrick, T.: Unsupervised text style transfer using language models as discriminators (2018). arXiv:abs/1805.11749

  28. Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., Weston, J.: Personalizing dialogue agents: I have a dog, do you have pets too? In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (vol. 1: Long Papers), pp. 2204–2213. Association for Computational Linguistics, Melbourne, Australia (2018). https://doi.org/10.18653/v1/P18-1205, https://aclanthology.org/P18-1205

  29. Zhang, Z., Zweigenbaum, P.: Gneg: graph-based negative sampling for word2vec (2018). https://doi.org/10.18653/v1/P18-2090

  30. Zhong, P., Sun, Y., Liu, Y., Zhang, C., Wang, H., Nie, Z., Miao, C.: Endowing empathetic dialogue systems with personas (2020). arXiv:abs/2004.12316

Download references

Acknowledgments

The research was financially supported the Russian Science Foundations (project 22-11-00128).

Author information

Authors and Affiliations

  1. ITMO University, Saint Petersburg, Russia

    Pavel Posokhov, Anastasia Matveeva, Olesia Makhnytkina, Anton Matveev & Yuri Matveev

Authors
  1. Pavel Posokhov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Anastasia Matveeva
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Olesia Makhnytkina
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Anton Matveev
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yuri Matveev
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Olesia Makhnytkina .

Editor information

Editors and Affiliations

  1. Indian Institute of Technology Dharwad, Dharwad, India

    S. R. Mahadeva Prasanna

  2. St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia

    Alexey Karpov

  3. Koneru Lakshmaiah Education Foundation, Vaddeswaram, India

    K. Samudravijaya

  4. KIIT Group of Colleges, Gurugram, India

    Shyam S. Agrawal

Rights and permissions

Reprints and permissions

Copyright information

© 2022 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Posokhov, P., Matveeva, A., Makhnytkina, O., Matveev, A., Matveev, Y. (2022). Personalizing Retrieval-Based Dialogue Agents. In: Prasanna, S.R.M., Karpov, A., Samudravijaya, K., Agrawal, S.S. (eds) Speech and Computer. SPECOM 2022. Lecture Notes in Computer Science(), vol 13721. Springer, Cham. https://doi.org/10.1007/978-3-031-20980-2_47

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-20980-2_47

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-20979-6

  • Online ISBN: 978-3-031-20980-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation