TY - GEN
T1 - Finding the best model among representative compositional models
AU - Muraoka, Masayasu
AU - Shimaoka, Sonse
AU - Yamamoto, Kazeto
AU - Watanabe, Yotaro
AU - Okazaki, Naoaki
AU - Inui, Kentaro
N1 - Funding Information:
This study was partly supported by Japan Society for the Promotion of Science (JSPS) KAKENHI Grant No. 23240018 and Japan Science and Technology Agency (JST)
Publisher Copyright:
Copyright 2014 by Masayasu Muraoka, Sonse Shimaoka, Kazeto Yamamoto.
PY - 2014
Y1 - 2014
N2 - The field of distributional-compositional semantics has yielded a range of computational models for composing the vector of a phrase from those of constituent word vectors. Existing models have various ranges of their expressiveness, recursivity, and trainability. However, these models have not been examined closely for their compositionality. We implement and compare these models under the same conditions. The experimentally obtained results demonstrate that the model using different composition matrices for different dependency relations achieved state-ofthe-art performance on a dataset for two-word compositions (Mitchell and Lapata, 2010).
AB - The field of distributional-compositional semantics has yielded a range of computational models for composing the vector of a phrase from those of constituent word vectors. Existing models have various ranges of their expressiveness, recursivity, and trainability. However, these models have not been examined closely for their compositionality. We implement and compare these models under the same conditions. The experimentally obtained results demonstrate that the model using different composition matrices for different dependency relations achieved state-ofthe-art performance on a dataset for two-word compositions (Mitchell and Lapata, 2010).
UR - http://www.scopus.com/inward/record.url?scp=84994092800&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84994092800&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84994092800
T3 - Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014
SP - 65
EP - 74
BT - Proceedings of the 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014
A2 - Boonkwan, Prachya
A2 - Aroonmanakun, Wirote
A2 - Supnithi, Thepchai
PB - Faculty of Pharmaceutical Sciences, Chulalongkorn University
T2 - 28th Pacific Asia Conference on Language, Information and Computation, PACLIC 2014
Y2 - 12 December 2014 through 14 December 2014
ER -