Position-aware deep multi-task learning for drug–drug interaction extraction

作者：

Highlights：

• A novel position-aware deep learning approach with is proposed for extracting DDIs.

• Binary DDI classification and interaction type identification are learned jointly.

• The proposed approach outperforms the state-of-the-art approaches on two tasks.

摘要

•A novel position-aware deep learning approach with is proposed for extracting DDIs.•Binary DDI classification and interaction type identification are learned jointly.•The proposed approach outperforms the state-of-the-art approaches on two tasks.

论文关键词：Classification,Multi-task learning,Drug–drug interaction extraction,Long short-term memory network

论文评审过程：Received 19 November 2017, Revised 26 February 2018, Accepted 11 March 2018, Available online 17 March 2018, Version of Record 28 May 2018.

论文官网地址：https://doi.org/10.1016/j.artmed.2018.03.001