Hybrid neural conditional random fields for multi-view sequence labeling

作者：

Highlights：

• We propose a hybrid neural CRF for multi-view sequence labeling, called MVCRF.

• Our model combines multi-view learning by utilizing consensus and complementary principles.

• We systematically compare the performance of MVCRF with other models.

• The experimental results show MVCRF achieves state-of-the-art performance.

摘要

•We propose a hybrid neural CRF for multi-view sequence labeling, called MVCRF.•Our model combines multi-view learning by utilizing consensus and complementary principles.•We systematically compare the performance of MVCRF with other models.•The experimental results show MVCRF achieves state-of-the-art performance.

论文关键词：Conditional random fields,Sequence labeling,Multi-view learning,Neural network,Dynamic programming

论文评审过程：Received 10 June 2019, Revised 16 September 2019, Accepted 22 October 2019, Available online 24 October 2019, Version of Record 16 January 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2019.105151