Hybrid neural conditional random fields for multi-view sequence labeling

doi:10.1016/j.knosys.2019.105151

Hybrid neural conditional random fields for multi-view sequence labeling

2020-02-01

11

PRE

AI

DOI：10.1016/j.knosys.2019.105151

Original

Original request for help

Save

Abstract

En 中文

In traditional machine learning, conditional random fields (CRF) is the mainstream probability model for sequence labeling problems. CRF considers the relation between adjacent labels other than decoding each label independently, and better performance is expected to achieve. However, there are few multiview learning methods involving CRF which can be directly used for sequence labeling tasks. In this paper, we propose a novel multi-view CRF model to label sequential data, called MVCRF, which well exploits two principles for multi-view learning: consensus and complementary. We first use different neural networks to extract features from multiple views. Then, considering the consistency among the different views, we introduce a joint representation space for the extracted features and minimize the distance between the two views for regularization. Meanwhile, following the complementary principle, the features of multiple views are integrated into the framework of CRF. We train MVCRF in an endto-end fashion and evaluate it on two benchmark data sets. The experimental results illustrate that MVCRF obtains state-of-the-art performance: F-1 score 95.44% for chunking on CoNLL-2000, 95.06% for chunking and 96.99% for named entity recognition (NER) on CoNLL-2003. (C) 2019 Elsevier B.V. All rights reserved.

Keywords:

Conditional random fields

Sequence labeling

Multi-view learning

Neural network

Dynamic programming

Hybrid neural conditional random fields for multi-view sequence labeling

Abstract

AI Summary

Journal

Organization