Abstract
Utterance domain classification (UDC) is a critical pre-processing step for many speech understanding and dialogue systems. Recently neural models have shown promising results on text classification. Meanwhile, the background information and knowledge beyond the utterance plays crucial roles in utterance comprehension. However, some improper background information and knowledge are easily introduced due to the ambiguity of entities or the noise in knowledge bases (KBs), UDC task remains a great challenge. To address this issue, this paper proposes a knowledge-gated (K-Gated) mechanism that leverages domain knowledge from external sources to control the path through which information flows in the neural network. We employ it with pre-trained token embedding from Bidirectional Encoder Representation from Transformers (BERT) into a wide spectrum of state-of-the-art neural text classification models. Experiments on the SMP-ECDT benchmark corpus show that the proposed method achieves a strong and robust performance regardless of the quality of the encoder models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sarikaya, R.: The technology behind personal digital assistants: an overview of the system architecture and key components. IEEE Signal Process. Mag. 34(1), 67–81 (2017)
Yu, K., Chen, R., Chen, B., et al.: Cognitive technology in task-oriented dialogue systems - concepts, advances and future. Chin. J. Comput. 38(12), 2333–2348 (2015). (in Chinese)
Kim, Y., Kim, D., Kumar, A.: Efficient large-scale neural domain classification with personalized attention. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), pp. 2214–2224 (2018)
Tür, G., Mori, R.: Spoken Language Understanding: Systems for Extracting Semantic Information from Speech. Wiley, Chichester (2011)
Xu, P., Sarikaya, R.: Contextual domain classification in spoken language understanding systems using recurrent neural network. In: Proceedings of the 39th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014), pp. 136–140 (2014)
Ke, Z., Huang, P., Zeng, Z.: Domain classification based on undefined utterances detection optimization. J. Chin. Inf. Process. 32(4), 105–113 (2018). (in Chinese)
Liu, B., Lane, I.: Attention-based recurrent neural network models for joint intent detection and slot filling. In: Proceedings of the 17th Annual Conference of the International Speech Communication Association (INTERSPEECH 2016), pp. 685–689 (2016)
Devlin, J., Chang, M., Lee, K., et al.: 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 (NAACL-HLT 2019), pp. 4171–4186 (2019)
Deng, Y., Shen, Y., Yang, M., et al.: Knowledge as a bridge: improving cross-domain answer selection with external knowledge. In: Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018), pp. 3295–3305 (2018)
Dauphin, Y.N., Fan, A., Auli, M., et al.: Language modeling with gated convolutional networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML 2017), pp. 933–941 (2017)
Shi, C., Liu, S., Ren, S., et al.: Knowledge-based semantic embedding for machine translation. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016), pp. 2245–2254 (2016)
Wang, J., Wang, Z., Zhang, D., Yan, J.: Combining knowledge with deep convolutional neural networks for short text classification. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI 2017), pp. 2915–2921 (2017)
Oord, A., Kalchbrenner, N., Espeholt, L., et al.: Conditional image generation with PixelCNN decoders. In: Proceedings of the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016), pp. 4790–4798 (2016)
Xue, W., Li, T.: Aspect based sentiment analysis with gated convolutional networks. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), pp. 2514–2523 (2018)
Heck, L., Tür, D., Tür, G.: Leveraging knowledge graphs for web-scale unsupervised semantic parsing. In: Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013), pp. 1594–1598 (2013)
Sarikaya, R., Hinton, G., Ramabhadran, B.: Deep belief nets for natural language call-routing. In: Proceedings of the 36th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2011), pp. 5680–5683 (2011)
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), pp. 1292–1302 (2014)
Ravuri, S., Stolcke, S.: A comparative study of recurrent neural network models for lexical domain classification. In: Proceedings of the 41st IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016), pp. 6075–6079 (2016)
Xiao, Y., Cho, K.: Efficient character-level document classification by combining convolution and recurrent layers. Computing Research Repository, arXiv:1602.00367. Version 1 (2016)
Cheng, J., Dong, L., Lapata, M.: Long short-term memory-networks for machine reading. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP 2016), pp. 551–561 (2016)
Vu, N.T., Gupta, P., Adel, H., et al.: Bi-directional recurrent neural network with ranking loss for spoken language understanding. In: Proceedings of the 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), pp. 6060–6064 (2016)
Yang, Z., Yang, D., Dyer, C., et al.: Hierarchical attention networks for document classification. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2016), pp. 1480–1489 (2016)
Chen, Y., Tur, D., Tür, G., et al.: Syntax or semantics? Knowledge-guided joint semantic frame parsing. In: Proceedings of 2016 IEEE Spoken Language Technology Workshop (SLT 2016), pp. 348–355 (2016)
Chen, J., Wang, A., Chen, J., et al.: CN-Probase: a data-driven approach for large-scale Chinese taxonomy construction. In: Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE 2019) (2019)
Moro, A., Raganato, A., Navigli, R.: Entity linking meets word sense disambiguation: a unified approach. Trans. Assoc. Comput. Linguist. 2, 231–244 (2013)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Proceedings of the 41st Annual Conference on Neural Information Processing Systems (NIPS 2017), pp. 6000–6010 (2017)
Boureau, Y., Ponce, J., LeCun, Y.: A theoretical analysis of feature pooling in visual recognition. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010), pp. 111–118 (2010)
Zhang, W., Chen, Z., Che, W., et al.: The first evaluation of Chinese human-computer dialogue technology. Computing Research Repository, arXiv:1709.10217. Version 1 (2017)
Acknowledgments
This work was supported by National Natural Science Foundation of China (No. 71472068), National Innovation Training Project for College Students of China (No. 201710564154), and Innovation Training Project for College Students of Guangdong Province (No. 201810564094). We also thank the SCIR Lab of Harbin Institute of Technology and the iFLYTEK Co. Ltd. for providing the SMP-ECDT benchmark corpus.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Du, Z., Huang, P., He, Y., Liu, W., Zhu, J. (2019). A Knowledge-Gated Mechanism for Utterance Domain Classification. In: Tang, J., Kan, MY., Zhao, D., Li, S., Zan, H. (eds) Natural Language Processing and Chinese Computing. NLPCC 2019. Lecture Notes in Computer Science(), vol 11839. Springer, Cham. https://doi.org/10.1007/978-3-030-32236-6_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-32236-6_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32235-9
Online ISBN: 978-3-030-32236-6
eBook Packages: Computer ScienceComputer Science (R0)