Skip to main navigation Skip to search Skip to main content

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

  • Zhijun Chen
  • , Hailong Sun*
  • , Wanhao Zhang
  • , Chunyi Xu
  • , Qianren Mao
  • , Pengpeng Chen
  • *Corresponding author for this work
  • Beihang University
  • Tsinghua University
  • Zhongguancun Laboratory
  • China's Aviation System Engineering Research Institute

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationKDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages274-285
Number of pages12
ISBN (Electronic)9798400701030
DOIs
StatePublished - 4 Aug 2023
Event29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 - Long Beach, United States
Duration: 6 Aug 202310 Aug 2023

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
ISSN (Print)2154-817X

Conference

Conference29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023
Country/TerritoryUnited States
CityLong Beach
Period6/08/2310/08/23

Keywords

  • crowdsourcing
  • information extraction
  • named entity recognition
  • noisy label
  • sequence labeling
  • weak supervision

Fingerprint

Dive into the research topics of 'Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler'. Together they form a unique fingerprint.

Cite this