@inproceedings{a11406d1acf44ec2a5203862ec13f520,
title = "Auto-dialabel: Labeling dialogue data with unsupervised learning",
abstract = "The lack of labeled data is one of the main challenges when building a task-oriented dialogue system. Existing dialogue datasets usually rely on human labeling, which is expensive, limited in size, and in low coverage. In this paper, we instead propose our framework auto-dialabel to automatically cluster the dialogue intents and slots. In this framework, we collect a set of context features, leverage an autoencoder for feature assembly, and adapt a dynamic hierarchical clustering method for intent and slot labeling. Experimental results show that our framework can promote human labeling cost to a great extent, achieve good intent clustering accuracy (84.1\%), and provide reasonable and instructive slot labeling results.",
author = "Chen Shi and Qi Chen and Lei Sha and Sujian Li and Xu Sun and Houfeng Wang and Lintao Zhang",
note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 ; Conference date: 31-10-2018 Through 04-11-2018",
year = "2018",
language = "英语",
series = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
publisher = "Association for Computational Linguistics",
pages = "684--689",
editor = "Ellen Riloff and David Chiang and Julia Hockenmaier and Jun'ichi Tsujii",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
address = "美国",
}