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

TL;DR

Neural-Hidden-CRF is a novel neural undirected graphical model that effectively leverages deep language models and hidden CRFs to improve weakly-supervised sequence labeling, achieving state-of-the-art results.

Contribution

It introduces a neuralized undirected graphical model with a hidden CRF layer that models sequence variables and weak labels, enhancing weak supervision tasks.

Findings

Achieved new state-of-the-art results on multiple benchmarks.

Outperformed recent models like CHMM by significant F1 score margins.

Demonstrated robustness and empirical power in weakly-supervised sequence labeling.

Abstract

We propose a neuralized undirected graphical model called Neural-Hidden-CRF to solve the weakly-supervised sequence labeling problem. Under the umbrella of probabilistic undirected graph 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.