TY - GEN
T1 - Developing Word Sense Disambiguation Corpuses Using Word2vec and Wu Palmer for Disambiguation
AU - Husein Wattiheluw, Fadli
AU - Sarno, Riyanarto
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/11/27
Y1 - 2018/11/27
N2 - In computational linguistics, meaning disambiguation is an open problem of natural language processing in the form of the process of identifying the meaning of the word polysemy used in a sentence. Resolving this problem, among others, has an impact on search engine relevance, anaphoric solving, coherence or cohesion, and inference or conclusion. Therefore, a study is needed that studies to find the meaning of a correct word on a topic. So that it affects the topics discussed in a sentence to find the true meaning. In this study, we focused on finding the meaning of words in a corpus-based sentence using word2vec and wu palmer. The word2vec algorithm is used to construct word vectors contained in sentences and wu palmer as an addition to new words that are not contained in the corpus, by assessing hypernym, meronym, and hyponym between words in sentences. The experimental results show that by adding a new word using wu palmer on corpus it can increase the precision value of 0.8232 in an introduction to a sentence contained in a topic, compared to not using the addition of a new word.
AB - In computational linguistics, meaning disambiguation is an open problem of natural language processing in the form of the process of identifying the meaning of the word polysemy used in a sentence. Resolving this problem, among others, has an impact on search engine relevance, anaphoric solving, coherence or cohesion, and inference or conclusion. Therefore, a study is needed that studies to find the meaning of a correct word on a topic. So that it affects the topics discussed in a sentence to find the true meaning. In this study, we focused on finding the meaning of words in a corpus-based sentence using word2vec and wu palmer. The word2vec algorithm is used to construct word vectors contained in sentences and wu palmer as an addition to new words that are not contained in the corpus, by assessing hypernym, meronym, and hyponym between words in sentences. The experimental results show that by adding a new word using wu palmer on corpus it can increase the precision value of 0.8232 in an introduction to a sentence contained in a topic, compared to not using the addition of a new word.
KW - Word sense disambiguation
KW - hypernym
KW - hyponym
KW - meronym
KW - word2vec
KW - wu palmer
UR - http://www.scopus.com/inward/record.url?scp=85060047294&partnerID=8YFLogxK
U2 - 10.1109/ISEMANTIC.2018.8549843
DO - 10.1109/ISEMANTIC.2018.8549843
M3 - Conference contribution
AN - SCOPUS:85060047294
T3 - Proceedings - 2018 International Seminar on Application for Technology of Information and Communication: Creative Technology for Human Life, iSemantic 2018
SP - 244
EP - 248
BT - Proceedings - 2018 International Seminar on Application for Technology of Information and Communication
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Seminar on Application for Technology of Information and Communication, iSemantic 2018
Y2 - 21 September 2018 through 22 September 2018
ER -