000000591 001__ 591
000000591 005__ 20260102124445.0
000000591 0247_ $$2DOI$$a10.6083/M4H41PFB
000000591 037__ $$aETD
000000591 245__ $$aA controlled study of the contribution of external resources on Chinese word segmentation
000000591 260__ $$bOregon Health and Science University
000000591 269__ $$a2011
000000591 336__ $$aThesis
000000591 502__ $$bM.S.
000000591 502__ $$gComputer Science & Electrical Engineering (sunsetting)
000000591 520__ $$aChinese word segmentation (CWS) is essential for natural language processing, yet written Chinese lacks explicit word boundaries. Recent CWS evaluations include closed tasks (training data only) and open tasks (external resources allowed), but the impact of external resources remains unclear. This study quantifies contributions of various resources and explores integration methods. Results show independent dictionaries significantly improve performance, a finding generalizable to other languages. Additionally, normalization of numbers, ASCII characters, and punctuation provides further gains. These findings offer practical guidance for optimizing open-task CWS systems
000000591 540__ $$fCC BY
000000591 542__ $$fIn copyright - single owner
000000591 650__ $$aArtificial Intelligence$$015109
000000591 650__ $$aMachine Learning$$011449
000000591 650__ $$aNatural Language Processing$$022716
000000591 650__ $$aLanguage$$021309
000000591 650__ $$aAsian People$$035483
000000591 6531_ $$adiscriminative method
000000591 6531_ $$achinese word segmentation
000000591 6531_ $$aChinese language
000000591 691__ $$aSchool of Medicine$$041369
000000591 692__ $$aDepartment of Biomedical Engineering$$041397
000000591 692__ $$aCenter for Spoken Language Understanding$$041388
000000591 7001_ $$aChen, Yongshun$$uOregon Health and Science University$$041354
000000591 7201_ $$aRoark, Brian$$uOregon Health and Science University$$041354$$7Personal$$eAdvisor
000000591 8564_ $$95ded2749-9546-4b29-8a7d-6ccb0a5e5196$$s598043$$uhttps://digitalcollections.ohsu.edu/record/591/files/592_etd.pdf$$ePublic$$2e4aaef636ae99470da67978b24929452$$31
000000591 905__ $$a/rest/prod/xw/42/n7/91/xw42n791k
000000591 909CO $$ooai:digitalcollections.ohsu.edu:591$$pstudent-work
000000591 980__ $$aTheses and Dissertations