Improve Chinese Clinical Named Entity Recognition Performance by Using the Graphical and Phonetic Feature

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract


Since Chinese language is quite different with English language, the machine cannot simply get the graphical and phonetic information form Chinese characters. Recent research on Chinese word embedding tries to use graphical information as subword. This paper uses both graphical and phonetic features to improve the performance of Chinese Clinical Named Entity Recognition. This research conducts and reports on an experiment performed to prove that the use of primary radical and pinyin can improve the performance of Clinical Named Entity Recognition and get the F-measure of 0.712

Bibliographical metadata

Original languageEnglish
Title of host publicationProceedings of BIBM 2018 (IEEE)
Pages1582-1586
Number of pages5
Publication statusPublished - 3 Dec 2018