A Two-channel model for relation extraction using multiple trained word embeddings

作者：

Highlights：

• A Two-channel model for relation extraction is proposed.

• The two channels are composed of a Bi-LSTM-ATT and a CNN.

• Multiple trained word embeddings are usded to alleviate polysemy problems.

摘要

•A Two-channel model for relation extraction is proposed.•The two channels are composed of a Bi-LSTM-ATT and a CNN.•Multiple trained word embeddings are usded to alleviate polysemy problems.

论文关键词：Relation extraction,Two-channel model,Trained word embedding

论文评审过程：Received 22 March 2022, Revised 1 August 2022, Accepted 12 August 2022, Available online 18 August 2022, Version of Record 1 September 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109701