Abstract
Dialogue systems need to deal with the unpredictability of user intents to track dialogue state and the heterogeneity of slots to understand user preferences. In this paper we investigate the hypothesis that solving these challenges as one unified model will allow the transfer of parameter support data across the different tasks. The proposed principled model is based on a Transformer encoder, trained on multiple tasks, and leveraged by a rich input that conditions the model on the target inferences. Conditioning the Transformer encoder on multiple target inferences over the same corpus, i.e., intent and multiple slot types, allows learning richer language interactions than a single-task model would be able to. In fact, experimental results demonstrate that conditioning the model on an increasing number of dialogue inference tasks leads to improved results: on the MultiWOZ dataset, the joint intent and slot detection can be improved by 3.2% by conditioning on intent, 10.8% by conditioning on slot and 14.4% by conditioning on both intent and slots. Moreover, on real conversations with Farfetch costumers, the proposed conditioned BERT can achieve high joint-goal and intent detection performance throughout a dialogue.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akoğlu, H.: User’s guide to correlation coefficients. Turkish J. Emerg. Med. 18, 91–93 (2018)
Budzianowski, P., Wen, T.H., Tseng, B.H., Casanueva, I., Stefan, U., Osman, R., Gašić, M.: Multiwoz - a large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue modelling. In: EMNLP (2018)
Chao, G.L., Lane, I.: BERT-DST: Scalable end-to-end dialogue state tracking with bidirectional encoder representations from transformer. In: INTERSPEECH (2019)
Chen, Q., Zhuo, Z., Wang, W.: Bert for joint intent classification and slot filling. arXiv:abs/1902.10909 (2019)
Clark, K., Khandelwal, U., Levy, O., Manning, C.D.: What does BERT look at? an analysis of BERT’s attention. In: Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 276–286 (2019)
Coucke, A., Saade, A., Ball, A., Bluche, T., Caulier, A., Leroy, D., Doumouro, C., Gisselbrecht, T., Caltagirone, F., Lavril, T., et al.: Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces. arXiv preprint arXiv:1805.10190 pp. 12–16 (2018)
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, Volume 1 (Long and Short Papers), pp. 4171–4186 (2019)
Eric, M., Goel, R., Paul, S., Sethi, A., Agarwal, S., Gao, S., Kumar, A., Goyal, A.K., Ku, P., Hakkani-Tür, D.: Multiwoz 2.1: A consolidated multi-domain dialogue dataset with state corrections and state tracking baselines. In: Calzolari, N., Béchet, F., Blache, P., Choukri, K., Cieri, C., Declerck, T., Goggi, S., Isahara, H., Maegaard, B., Mariani, J., Mazo, H., Moreno, A., Odijk, J., Piperidis, S. (eds.) Proceedings of The 12th Language Resources and Evaluation Conference, LREC 2020, Marseille, France, May 11–16, 2020, pp. 422–428. European Language Resources Association (2020). https://aclanthology.org/2020.lrec-1.53/
Hakkani-Tur, D., Tur, G., Celikyilmaz, A., Chen, Y.N., Gao, J., Deng, L., Wang, Y.Y.: Multi-domain joint semantic frame parsing using bi-directional rnn-lstm. In: Proceedings of Interspeech (2016)
Han, T., Liu, X., Takanobu, R., Lian, Y., Huang, C., Wan, D., Peng, W., Huang, M.: Multiwoz 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation. In: Proceedings of the 10th CCF International Conference on Natural Language Processing and Chinese Computing, pp. 206–218. CCF (2021)
Heck, M., van Niekerk, C., Lubis, N., Geishauser, C., Lin, H., Moresi, M., Gasic, M.: Trippy: A triple copy strategy for value independent neural dialog state tracking. In: Pietquin, O., Muresan, S., Chen, V., Kennington, C., Vandyke, D., Dethlefs, N., Inoue, K., Ekstedt, E., Ultes, S. (eds.) Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGdial 2020, 1st virtual meeting, July 1–3, 2020, pp. 35–44. Association for Computational Linguistics (2020). https://aclanthology.org/2020.sigdial-1.4/
Hosseini-Asl, E., McCann, B., Wu, C.S., Yavuz, S., Socher, R.: A simple language model for task-oriented dialogue. NeurIPS 2020-December (5 2020)
Manku, G., Lee-Thorp, J., Kanagal, B., Ainslie, J., Feng, J., Pearson, Z., Anjorin, E., Gandhe, S., Eckstein, I., Rosswog, J., Sanghai, S., Pohl, M., Adams, L., Sivakumar, D.: Shoptalk: A system for conversational faceted search. CoRR (2021), arxiv.org/abs/2109.00702
Pouran Ben Veyseh, A., Dernoncourt, F., Nguyen, T.H.: Improving slot filling by utilizing contextual information. In: Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI, pp. 90–95 (2020)
Qian, K., Beirami, A., Lin, Z., De, A., Geramifard, A., Yu, Z., Sankar, C.: Annotation inconsistency and entity bias in MultiWOZ. In: Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 326–337 (2021)
Qin, L., Che, W., Li, Y., Wen, H., Liu, T.: A stack-propagation framework with token-level intent detection for spoken language understanding. In: EMNLP-IJCNLP, pp. 2078–2087 (2019)
Rastogi, A., Zang, X., Sunkara, S., Gupta, R., Khaitan, P.: Towards scalable multi-domain conversational agents: the schema-guided dialogue dataset. In: AAAI (2020)
Shah, P., Hakkani-Tür, D., Liu, B., Tür, G.: Bootstrapping a neural conversational agent with dialogue self-play, crowdsourcing and on-line reinforcement learning. In: NAACL, pp. 41–51 (2018)
Sousa, R.G., Ferreira, P.M., Costa, P.M., Azevedo, P., Costeira, J.P., Santiago, C., Magalhaes, J., Semedo, D., Ferreira, R., Rudnicky, A.I., Hauptmann, A.G.: Ifetch: multimodal conversational agents for the online fashion marketplace. In: Proceedings of the 2nd ACM Multimedia Workshop on Multimodal Conversational AI, pp. 25–26. MuCAI’21, Association for Computing Machinery, New York (2021). https://doi.org/10.1145/3475959.3485395
Wu, C.S., Hoi, S.C., Socher, R., Xiong, C.: TOD-BERT: Pre-trained natural language understanding for task-oriented dialogue. In: EMNLP, pp. 917–929 (2020)
Wu, C.S., Madotto, A., Hosseini-Asl, E., Xiong, C., Socher, R., Fung, P.: Transferable multi-domain state generator for task-oriented dialogue systems. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 808–819 (2019)
Wu, D., Ding, L., Lu, F., Xie, J.: SlotRefine: A fast non-autoregressive model for joint intent detection and slot filling. In: EMNLP, pp. 1932–1937 (2020)
Xu, P., Hu, Q.: An end-to-end approach for handling unknown slot values in dialogue state tracking. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1448–1457 (2018)
Zang, X., Rastogi, A., Sunkara, S., Gupta, R., Zhang, J., Chen, J.: Multiwoz 2.2: A dialogue dataset with additional annotation corrections and state tracking baselines. In: Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI, ACL 2020, pp. 109–117 (2020)
Zeng, Y., Nie, J.Y.: Multi-domain dialogue state tracking - a purely transformer-based generative approach (2020)
Zhang, J., Hashimoto, K., Wu, C., Wan, Y., Yu, P.S., Socher, R., Xiong, C.: Find or classify? dual strategy for slot-value predictions on multi-domain dialog state tracking. CoRR (2019). arxiv.org/abs/1910.03544
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
Tavares, D., Azevedo, P., Semedo, D., Sousa, R., Magalhães, J. (2023). Task Conditioned BERT for Joint Intent Detection and Slot-Filling. In: Moniz, N., Vale, Z., Cascalho, J., Silva, C., Sebastião, R. (eds) Progress in Artificial Intelligence. EPIA 2023. Lecture Notes in Computer Science(), vol 14115. Springer, Cham. https://doi.org/10.1007/978-3-031-49008-8_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-49008-8_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49007-1
Online ISBN: 978-3-031-49008-8
eBook Packages: Computer ScienceComputer Science (R0)