TY - GEN
T1 - Improving hypernymy detection with an integrated path-based and distributional method
AU - Shwartz, Vered
AU - Goldberg, Yoav
AU - Dagan, Ido
N1 - Publisher Copyright:
© 2016 Association for Computational Linguistics.
PY - 2016/1/1
Y1 - 2016/1/1
N2 - Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complementary approaches. Distributional methods, whose supervised variants are the current best performers, and path-based methods, which received less research attention. We suggest an improved path-based algorithm, in which the dependency paths are encoded using a recurrent neural network, that achieves results comparable to distributional methods. We then extend the approach to integrate both path-based and distributional signals, significantly improving upon the state-of-the-art on this task.
AB - Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complementary approaches. Distributional methods, whose supervised variants are the current best performers, and path-based methods, which received less research attention. We suggest an improved path-based algorithm, in which the dependency paths are encoded using a recurrent neural network, that achieves results comparable to distributional methods. We then extend the approach to integrate both path-based and distributional signals, significantly improving upon the state-of-the-art on this task.
UR - https://www.scopus.com/pages/publications/85011967258
U2 - 10.18653/v1/p16-1226
DO - 10.18653/v1/p16-1226
M3 - Conference contribution
AN - SCOPUS:85011967258
T3 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
SP - 2389
EP - 2398
BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
PB - Association for Computational Linguistics (ACL)
T2 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
Y2 - 7 August 2016 through 12 August 2016
ER -