TY - GEN
T1 - Preposition sense disambiguation and representation
AU - Gong, Hongyu
AU - Mu, Jiaqi
AU - Bhat, Suma
AU - Viswanath, Pramod
N1 - Funding Information:
This work is supported by IBM-ILLINOIS Center for Cognitive Computing Systems Research (C3SR) - a research collaboration as part of the IBM AI Horizons Network. We thank EMNLP anonymous reviewers for their constructive suggestions.
Publisher Copyright:
© 2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - Prepositions are highly polysemous, and their variegated senses encode significant semantic information. In this paper we match each preposition's left- and right context, and their interplay to the geometry of the word vectors to the left and right of the preposition. Extracting these features from a large corpus and using them with machine learning models makes for an efficient preposition sense disambiguation (PSD) algorithm, which is comparable to and better than state-of-the-art on two benchmark datasets. Our reliance on no linguistic tool allows us to scale the PSD algorithm to a large corpus and learn sense-specific preposition representations. The crucial abstraction of preposition senses as word representations permits their use in downstream applications-phrasal verb paraphrasing and preposition selection-with new state-ofthe-art results.
AB - Prepositions are highly polysemous, and their variegated senses encode significant semantic information. In this paper we match each preposition's left- and right context, and their interplay to the geometry of the word vectors to the left and right of the preposition. Extracting these features from a large corpus and using them with machine learning models makes for an efficient preposition sense disambiguation (PSD) algorithm, which is comparable to and better than state-of-the-art on two benchmark datasets. Our reliance on no linguistic tool allows us to scale the PSD algorithm to a large corpus and learn sense-specific preposition representations. The crucial abstraction of preposition senses as word representations permits their use in downstream applications-phrasal verb paraphrasing and preposition selection-with new state-ofthe-art results.
UR - http://www.scopus.com/inward/record.url?scp=85081752562&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081752562&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85081752562
T3 - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
SP - 1510
EP - 1521
BT - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
A2 - Riloff, Ellen
A2 - Chiang, David
A2 - Hockenmaier, Julia
A2 - Tsujii, Jun'ichi
PB - Association for Computational Linguistics
T2 - 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Y2 - 31 October 2018 through 4 November 2018
ER -