Research on Joint Modeling of Intent Detection and Slot Filling

Yang, Dan; Geng, Chaoyang; Li, Yi

doi:10.2478/ijanmc-2023-0059

Abstract

In task-based dialogue system, the key of the natural language understanding module is intent detection and slot filling. At this stage, Joint modeling of intention detection and slot filling tasks has become the mainstream and achieved good results. In order to investigate the correlation between intention detection and slot filling tasks, Joint model of intention detection and slot filling based on attention mechanism in three dimensions: one-way modeling from intention to slot, Unidirectional modeling from slot to intention and bidirectional modeling from intention to slot Separately. And experiments were conducted using the Chinese dataset CAIS, and the results showed three evaluation results for time slot F1.The intention accuracy and overall accuracy of joint models for intention detection and filling gaps are usually higher than those of unidirectional models.

References

Research on how to understand natural language in task dialogues based on deep learning [D] Xi'an University of Electronic Science and Technology 2021, DOI: 10.27389/d.cnki.gxadu.2021.003266.
Open DOI Search in Google Scholar Back to article
Guo Suchao, Hao Xia, Yao Xiaobo, and Li Lin. Study on Quiz intention recognition and slot filling joint model of agricultural pest knowledge [J]. Journal of Agricultural Machinery, 2023, 54 (01): 205–215
Search in Google Scholar Back to article
Zhang J, Bui T, Yoon S, et al. Few Shot Intent Detection via Contrastive Pre Training and Fine Tuning [J]. 2021.
Search in Google Scholar Back to article
Goo CW, Gao G, Hsu YK, et al. Slot strobe modeling is used for joint time slot filling and intention prediction. In: Proc of Conf., North American Chapter of Computational Linguistics Association.: Human Language Technology, Vol. 2. 2018. 753 – 757.
Search in Google Scholar Back to article
Haihong E, Beiqing Niu, Zhong Fuchen, and Meinasong, “a novel two-way interconnection model is used for joint intention detection and slotting,” in ACL Proc., 2019.
Search in Google Scholar Back to article
Liu Yijin, fan Dongmeng, Zhang Jinchao, Zhou Jie, Chen Yufeng, and Jinan Xu, “CM net: novel collaborative memory network for oral understanding,” in Proc., 2019 of emnlp.
Search in Google Scholar Back to article
Teng, Qin, Automobile, ecc. Improve your understanding of spoken Chinese through the [C]//International Conference on Voice and Signal Processing IEEE, 2020.
Search in Google Scholar Back to article
Qin l, Liu T, cut W, etc. Interactive Codec for Joint Slot Filling and Intent Detection [C]//International Conference on Acoustics, Sound, and Signal Processing IEEE, 2021.
Search in Google Scholar Back to article
Zhang, H. Wang. A Joint Model for Identifying Understanding Oral Intention and Filling Gaps. Extracted from: The Process of the International Federation of Artificial Intelligence 25th edition 2016.2993–2999
Search in Google Scholar Back to article
Haffner P, Tur G, Wright JH. Optimize SVM for complex call classification. In: Process International Acoustics Conference and Signal Processing. IEEE (ICASSP 2003) Volume 1 IEEE, 2003.632–635
Search in Google Scholar Back to article
Shapire RE, Singer Y. BoosTexter: A Text Sorting System Based on Boosting. Machine Learning, 2000, 39 (2): 135–168.
Search in Google Scholar Back to article
Wei P.F., Zeng B., Wang M.H., and Zeng A. Review of Speech Understanding Joint Modeling Algorithms Based on Deep Learning [J]Software Magazine, 2022, 33 (11): 41924216.DOI:10.13328/j.cnki.jos.006385.
Open DOI Search in Google Scholar Back to article
Yu Bengang, mladší bratr Fan Zhao Review of Natural language processing conditions and airport model research [J]Journal of information resource management, 2020, 10 (05): 96111. doi:10.13365/j.jirm.2020.05.096.
Open DOI Search in Google Scholar Back to article
Xu P, Sarikaya R. Triangle CRF based on convolutional neural network is used for joint intention detection and slot filling [C] / / / automatic speech recognition and understanding (asru), IEEE workshop in 2013. IEEE, 2013.DOI:10.1109/ASRU.2013.6707709. Neter J R, Guzide O. Deep learning in natural language processing [J]. 2018(1).
Open DOI Search in Google Scholar Back to article
Ravuri S V, Stolcke A. Repetitive Neural Networks and LSTM Models for Word Pronunciation Classification [C]//2015DOI:10.21437/Interlingua2015 42.
Search in Google Scholar Back to article
Nij, Young T, pandelea V et coll. Research progress in dialogue systems based on deep learning [J]2021.
Search in Google Scholar Back to article
Yu, Xie En, JinRNN semantic frame analysis model, using dual models for intention detection and time slot filling [J]2018.
Search in Google Scholar Back to article
Zhang C, Li Yi, doon et al. Filling and intention testing combination based on neural capsule network [C]//annual paper collection 57 Society for Computational linguistics 2019.
Search in Google Scholar Back to article

Research on Joint Modeling of Intent Detection and Slot Filling

Abstract

Paradigm

My account