Multi-task and multi-view training for end-to-end relation extraction

Junchi Zhang

doi:10.1016/j.neucom.2019.06.087

Multi-task and multi-view training for end-to-end relation extraction

2019-10-01

14

PRE

AI

DOI：10.1016/j.neucom.2019.06.087

原文链接

原文求助

摘要

En 中文

Transfer learning has shown promising results for transferring knowledge of source tasks to target tasks in natural language processing (NLP). In this paper, we investigate a multi-task and multi-view learning (MTMVL) framework for end-to-end neural relation extraction, using large noisy data as one auxiliary task for improving manually labeled data, and a dependency parsing objective as a second auxiliary task for leveraging syntax. Two views are taken for relation extraction, consisting of a joint tagging view and a novel context relation view. To capture sentence multi-level information, we explore a weighted average approach to represent shared deep bi-directional recurrent neural networks and encourage auxiliary tasks to accommodate relation extraction task via a time-related scheduled sampling strategy. We evaluate MTMVL framework on manual-labeled ACE2005 dataset, and experimental results show that our model outperforms the state-of-the-art methods, which indicates the effectiveness of multi-auxiliary information for knowledge transferring. (C) 2019 Elsevier B.V. All rights reserved.

Keyword:

Relation extraction

Transfer learning

Multi-task learning

Multi-view learning

Deep learning

Multi-task and multi-view training for end-to-end relation extraction

摘要

AI总结

期刊

机构

引用论文