A Hybrid Method for Extracting Turkish Part-Whole Relation Pairs from Corpus
dc.authorid | Yildiz, Tugba/0000-0002-8552-2806; | |
dc.authorwosid | Yildiz, Tugba/ABC-5958-2020 | |
dc.authorwosid | Diri, Banu/AAA-1020-2021 | |
dc.contributor.author | Sahin, Gurkan | |
dc.contributor.author | Diri, Banu | |
dc.contributor.author | Yildiz, Tugba | |
dc.date.accessioned | 2024-07-18T20:52:15Z | |
dc.date.available | 2024-07-18T20:52:15Z | |
dc.date.issued | 2016 | |
dc.department | İstanbul Bilgi Üniversitesi | en_US |
dc.description | 24th Signal Processing and Communication Application Conference (SIU) -- MAY 16-19, 2016 -- Zonguldak, TURKEY | en_US |
dc.description.abstract | Extraction of various semantic relation pairs from different sources (dictionary definitions, corpus etc.) with high accuracy is one of the most popular topics in natural language processing (NLP). In this study, a hybrid method is proposed to extract Turkish part-whole pairs from corpus. Corpus statistics, WordNet similarities and Word2Vec word vector similarities are used together in this study. Firstly, initial part-whole seeds are prepared and by using these seeds part-whole patterns are extracted from corpus. For each pattern, a reliability score is calculated and reliable patterns are selected to produce new pairs from corpus. Various reliability scores are used for new pairs. To measure success of method, 19 target whole words are selected and average 83% (first 10 pairs), 74% (first 20 pairs), 68% (first 30 pairs) precisions are obtained, respectively. | en_US |
dc.description.sponsorship | IEEE,Bulent Ecevit Univ, Dept Elect & Elect Engn,Bulent Ecevit Univ, Dept Biomed Engn,Bulent Ecevit Univ, Dept Comp Engn | en_US |
dc.identifier.endpage | 1040 | en_US |
dc.identifier.isbn | 978-1-5090-1679-2 | |
dc.identifier.scopus | 2-s2.0-84982812281 | en_US |
dc.identifier.scopusquality | N/A | en_US |
dc.identifier.startpage | 1037 | en_US |
dc.identifier.uri | https://hdl.handle.net/11411/8598 | |
dc.identifier.wos | WOS:000391250900236 | en_US |
dc.identifier.wosquality | N/A | en_US |
dc.indekslendigikaynak | Web of Science | en_US |
dc.indekslendigikaynak | Scopus | en_US |
dc.language.iso | tr | en_US |
dc.publisher | IEEE | en_US |
dc.relation.ispartof | 2016 24th Signal Processing and Communication Application Conference (Siu) | en_US |
dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Part-Whole Semantic Relationship | en_US |
dc.subject | Pattern Based Method | en_US |
dc.subject | Lexico-Syntactic Pattern | en_US |
dc.subject | Semantic Dictionary | en_US |
dc.subject | Natural Language Processing | en_US |
dc.title | A Hybrid Method for Extracting Turkish Part-Whole Relation Pairs from Corpus | en_US |
dc.type | Conference Object | en_US |