Multi-Task Learning for Chemical Named Entity Recognition with Chemical Compound Paraphrasing

DOI DOI Web Site 2 Citations 39 References Open Access

Bibliographic Information

Other Title
  • 化学分野の固有表現抽出のための化合物名を含む文の言い換え学習を用いたマルチタスク学習手法

Search this article

Description

<p>We propose a method to improve named entity recognition (NER) for chemical compounds using multi-task learning by jointly training a chemical NER model and a chemical compound name paraphrase model. Our method enables the NER model to capture chemical compound paraphrases by sharing the parameters of NER and the character embeddings based on long short-term memories (LSTM) with the paraphrase model. Experimental results on BioCreative IV CHEMDNER show that our method learning paraphrase contributes to improved accuracy. </p>

Journal

Citations (2)*help

See more

References(39)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top