一种结合话语伪标签注意力的人机对话意图分类方法(A Human-machine Dialogue Intent Classification Method using Utterance Pseudo Label Attention)

Jiande Ding (丁健德), Peijie Huang (黄沛杰), Jiabao Xu (许嘉宝), Youming Peng (彭佑铭)


Abstract
在人机对话中,系统需要通过意图分类判断用户意图,再触发相应的业务类型。由于多轮人机对话具有口语化、长文本和特征稀疏等特点,现有的文本分类方法在人机对话意图分类上还存在较大困难。本文在层次注意力网络(hierarchical attention networks, HAN)基础上,提出了一种结合话语伪标签注意力的层次注意力网络模型PLA-HAN (HAN with utterance pseudo label attention)。PLA-HAN通过优选伪标签集、构建单句话语意图识别模型以及设计话语伪标签注意力机制,识别单句话语意图伪标签,并计算话语伪标签注意力。进而将单句话语伪标签注意力嵌入到HAN的层级结构中,与HAN中的句子级别注意力相融合。融合了单句话语意图信息的句子级注意力使模型整体性能得到进一步的提升。我们在中国中文信息学会主办的“客服领域用户意图分类评测比赛”的评测语料上进行实验,实验结果证明PLA-HAN模型取得了优于HAN等对比方法的意图分类性能。
Anthology ID:
2020.ccl-1.27
Volume:
Proceedings of the 19th Chinese National Conference on Computational Linguistics
Month:
October
Year:
2020
Address:
Haikou, China
Editors:
Maosong Sun (孙茂松), Sujian Li (李素建), Yue Zhang (张岳), Yang Liu (刘洋)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
277–287
Language:
Chinese
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.ccl-1.27/
DOI:
Bibkey:
Cite (ACL):
Jiande Ding, Peijie Huang, Jiabao Xu, and Youming Peng. 2020. 一种结合话语伪标签注意力的人机对话意图分类方法(A Human-machine Dialogue Intent Classification Method using Utterance Pseudo Label Attention). In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 277–287, Haikou, China. Chinese Information Processing Society of China.
Cite (Informal):
一种结合话语伪标签注意力的人机对话意图分类方法(A Human-machine Dialogue Intent Classification Method using Utterance Pseudo Label Attention) (Ding et al., CCL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2020.ccl-1.27.pdf