Lee Y.-Y.Yen T.-Y.Huang H.-H.HSIN-HSI CHEN2019-07-102019-07-1020179781450349185https://scholars.lib.ntu.edu.tw/handle/123456789/413085With the aid of recently proposed word embedding algorithms, the study of semantic relatedness has progressed and advanced rapidly. In this research, we propose a novel structural-fitting method that utilizes the linguistic ontology into vector space representations. The ontological information is applied in two ways. The fine2coarse approach refines the word vectors from fine-grained to coarse-grained terms1 (word types), while the coarse2fine approach refines the word vectors from coarsegrained to fine-grained terms. In the experiments, we show that our proposed methods outperform previous approaches in seven publicly available benchmark datasets. ? 2017 Association for Computing Machinery.Linguistic ontologyRetrofittingSemantic relatednessStructural-fittingWord embeddingStructural-fitting word vectors to linguistic ontology for semantic relatedness measurementconference paper10.1145/3132847.31331522-s2.0-85037340610https://www.scopus.com/inward/record.uri?eid=2-s2.0-85037340610&doi=10.1145%2f3132847.3133152&partnerID=40&md5=c6b09759cf9b2c159a60c25ef50f3484