跳到主要导航 跳到搜索 跳到主要内容

Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler

  • Zhijun Chen
  • , Hailong Sun*
  • , Wanhao Zhang
  • , Chunyi Xu
  • , Qianren Mao
  • , Pengpeng Chen
  • *此作品的通讯作者
  • Beihang University
  • Tsinghua University
  • Zhongguancun Laboratory
  • China's Aviation System Engineering Research Institute

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

We propose a neuralized undirected graphical model called Neural-Hidden-CRF to solve the weakly-supervised sequence labeling problem. Under the umbrella of undirected graphical theory, the proposed Neural-Hidden-CRF embedded with a hidden CRF layer models the variables of word sequence, latent ground truth sequence, and weak label sequence with the global perspective that undirected graphical models particularly enjoy. In Neural-Hidden-CRF, we can capitalize on the powerful language model BERT or other deep models to provide rich contextual semantic knowledge to the latent ground truth sequence, and use the hidden CRF layer to capture the internal label dependencies. Neural-Hidden-CRF is conceptually simple and empirically powerful. It obtains new state-of-the-art results on one crowdsourcing benchmark and three weak-supervision benchmarks, including outperforming the recent advanced model CHMM by 2.80 F1 points and 2.23 F1 points in average generalization and inference performance, respectively.

源语言英语
主期刊名KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
出版商Association for Computing Machinery
274-285
页数12
ISBN(电子版)9798400701030
DOI
出版状态已出版 - 4 8月 2023
活动29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 - Long Beach, 美国
期限: 6 8月 202310 8月 2023

出版系列

姓名Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
ISSN(印刷版)2154-817X

会议

会议29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023
国家/地区美国
Long Beach
时期6/08/2310/08/23

指纹

探究 'Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler' 的科研主题。它们共同构成独一无二的指纹。

引用此