Abstract
Extracting context from natural language conversations has been the focus of applications which communicate with humans. Understanding the meaning and the intent of the user input, and formulating responses based on a contextual analysis mimicking that of an actual person is at the heart of modern-day chatbots and conversational agents. For this purpose, dialogue systems often use context from previous dialogue history. Thus, present-day dialogue systems typically parse over user utterances and sort them into semantic frames. In this paper, a bidirectional RNN with LSTM and a CRF layer on top is used to classify each utterance into its resultant dialogue act. Furthermore, there is a separate bidirectional RNN with LSTM and attention for the purpose of slot tagging. Slot annotations use the inside-outside-beginning (IOB) scheme. Softmax regression is used to determine the intent of the entire conversation. The approach is demonstrated on data from three different domains.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sordoni A, Bengio Y, Vahabi H, Lioma C, Simonsen JG, Nie J-Y (2015) A hierarchical recurrent encoder-decoder for generative context-aware query suggestion. In: Proceedings of the 24th ACM international on conference on information and knowledge management, pp 553–562
Serbian V, Sordoni A, Bengio Y, Courville A, Pineau J (2016) Building end-to-end dialogue systems using generative hierarchical neural network models. In: Proceedings of the 13th AAAI conference artificial intelligence, pp 3776–3783
Serban V, Sordoni A, Lowe R, Charlin L, Pineau J, Courville A, Bengio Y (2017) A hierarchical latent variable encoder-decoder model for generating dialogues. In: Proceedings of the 31st AAAI conference artificial intelligence, pp 3295–3301
Kumar H, Agarwal A, Dasgupta R, Joshi S, Kumar A (2017) Dialogue act sequence labelling using hierarchical encoder with CRF. Preprint at arXiv:1709.04250v2
Mesnil G et al (2015) Using recurrent neural networks for slot filling in spoken language understanding. IEEE/ACM Trans Audio Speech Lang Process 23(3):530–539
Lafferty J, McCallum A, Pereira FCN (2001) Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th international conference machine learning, pp 282–289
McCallum A, Freitag D, Pereira F (2000) Maximum entropy markov models for information extraction and segmentation. In: Proceedings of the 17th international conference machine learning, pp 591–598
Baidu ZH, Baidu WX, Yu K (2015) Bidirectional LSTM-CRF models for sequence tagging. Preprint at arXiv:1508.01991v1
Gupta R, Rastogi A, Hakkani-Tur D (2018) An efficient approach to encoding context for spoken language understanding. Preprint at arXiv:1807.00267v1
Liu B, Lane I (2016) Attention-based recurrent neural network models for joint intent detection and slot filling. Preprint at arXiv:1609.01454
Li X, Panda S, Liu J, Gao J Microsoft dialogue challenge: building end-to-end task-completion dialogue system. Microsoft, Redmond, WA
Li X, Lipton ZC, Dhingra B, Li L, Gao J, Chen Y-N (2017) A user simulator for task completion dialogues. Preprint at arXiv:1612.05688v3
Bahdanau D, Cho K, Bengio Y (2016) Neural machine translation by jointly learning to align and translate. Preprint at arXiv:1409.0473v7
Batista DS (2017) Conditional random fields for sequence prediction. [Online]. Available http://www.davidsbatista.net/blog/2017/11/13/Conditional_Random_Fields. Accessed on 19 May 2019
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Chauhan, A., Malhotra, A., Singh, A., Arora, J., Shukla, S. (2020). Encoding Context in Task-Oriented Dialogue Systems Using Intent, Dialogue Acts, and Slots. In: Saini, H., Sayal, R., Buyya, R., Aliseri, G. (eds) Innovations in Computer Science and Engineering. Lecture Notes in Networks and Systems, vol 103. Springer, Singapore. https://doi.org/10.1007/978-981-15-2043-3_34
Download citation
DOI: https://doi.org/10.1007/978-981-15-2043-3_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-2042-6
Online ISBN: 978-981-15-2043-3
eBook Packages: EngineeringEngineering (R0)