Abstract
Customer service question answering have recently seen increased interest in NLP due to their potential commercial values. However, existing methods are largely based on Deep Neural Networks (DNNs) that are computationally expensive and memory intensive, which hinder their deployment in many real-world scenarios. In addition, the customer service dialogue data is very domain-specific, and it is difficult to achieve a high matching accuracy without specific model optimization. In this paper, we propose CFTM, A Coarse-to-Fine Text Matching Framework, which consists of Fasttext coarse-grained classification, and Roformer-sim fine-grained sentence vector matching. This Coarse-to-Fine structure can effectively reduce the amount of model parameters and speed up system inference. We also use the CoSENT loss function to optimize the Roformer-sim model according to the characteristics of customer service dialogue data, which effectively improves the matching accuracy of the framework. We conduct extensive experiments on CHUZHOU and EIP customer service questioning datasets from KONKA. The result shows that CFTM outperforms baselines across all metrics, achieving a 2.5 improvement in F1-Score and a 30% improvement in inference time, which demonstrates that our CFTM gets higher response accuracy and faster interaction speed in customer service question answering.
A. Li and X. Liang—These authors contributed equally to this work.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Wen, T., Gasic, M., Mrksic, N., Su, P., Vandyke, D., Young, S.J.: Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. The Association for Computational Linguistics (2015)
Wang, S., Jiang, J.: A compare-aggregate model for matching text sequences. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, Conference Track Proceedings, OpenReview.net (2017)
Huang, P., He, X., Gao, J., Deng, L., Acero, A., Heck, L.P.: Learning deep structured semantic models for web search using clickthrough data. In: ACM (2013)
Shen, Y., He, X., Gao, J., Deng, L., Mesnil, G.: Learning semantic representations using convolutional neural networks for web search. In: ACM (2014)
Hu, B., Lu, Z., Li, H., Chen, Q.: Convolutional neural network architectures for matching natural language sentences. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q., eds Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, pp. 2042–2050. Montreal, Quebec, Canada (2014)
Mueller, J., Thyagarajan, A.: Siamese recurrent architectures for learning sentence similarity. In: AAAI Press (2016)
Wan, S., Lan, Y., Guo, J., Xu, J., Pang, L., Cheng, X.: A deep architecture for semantic matching with multiple positional sentence representations. In: AAAI Press (2016)
Pang, L., Lan, Y., Guo, J., Xu, J., Wan, S., Cheng, X.: Text matching as image recognition. In: AAAI Press (2016)
Wang, Z., Hamza, W., Florian, R.: Bilateral multi-perspective matching for natural language sentences (2017)
Chen, Q., Zhu, X., Ling, Z., Wei, S., Jiang, H., Inkpen, D.: Enhanced LSTM for natural language inference. Association for Computational Linguistics (2017)
Qiao, Y., Xiong, C., Liu, Z., Liu, Z.: Understanding the behaviors of BERT in ranking. CoRR abs/1904.07531 (2019)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Association for Computational Linguistics (2019)
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. In: Association for Computational Linguistics (2019)
Su, J.: Simbertv2 is here! fusion of retrieved and generated Roformer-sim models (In Chinese) (2021)
Lu, Z., Li, H.: A deep architecture for matching short texts. In: Burges, C.J.C., Bottou, L., Ghahramani, Z., Weinberger, K.Q., eds Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held, pp. 1367–1375. Lake Tahoe, Nevada, United States (2013)
Guo, J., Fan, Y., Ai, Q., Croft, W.B.: A deep relevance matching model for ad-hoc retrieval. In: ACM (2016)
Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. In: Association for Computational Linguistics (2017)
Su, J.: Cosent (1): a more efficient sentence vector scheme than sentence-BERT (In Chinese) (2022)
Jiao, X., et al.: Tinybert: distilling BERT for natural language understanding. Volume EMNLP 2020 of Findings of ACL. In: Association for Computational Linguistics (2020)
Sun, Y., et al.: ERNIE 3.0: large-scale knowledge enhanced pre-training for language understanding and generation. CoRR abs/2107.02137 (2021)
Acknowledgments
We thank all anonymous reviewers for their helpful comments. This work was partially supported by the National Natural Science Foundation of China (62006062, 62176076), Shenzhen Foundational Research Funding JCYJ20200109113441941, Shenzhen Key Technology Project JSGG20210802154400001, and Joint Lab of HITSZ and Konka.
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 Switzerland AG
About this paper
Cite this paper
Li, A. et al. (2022). A Coarse-to-Fine Text Matching Framework for Customer Service Question Answering. In: Yang, Y., Wang, X., Zhang, LJ. (eds) Cognitive Computing – ICCC 2022. ICCC 2022. Lecture Notes in Computer Science, vol 13734. Springer, Cham. https://doi.org/10.1007/978-3-031-23585-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-23585-6_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23584-9
Online ISBN: 978-3-031-23585-6
eBook Packages: Computer ScienceComputer Science (R0)