Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations

Vered Shwartz, Ido Dagan


Abstract
Recognizing various semantic relations between terms is beneficial for many NLP tasks. While path-based and distributional information sources are considered complementary for this task, the superior results the latter showed recently suggested that the former’s contribution might have become obsolete. We follow the recent success of an integrated neural method for hypernymy detection (Shwartz et al., 2016) and extend it to recognize multiple relations. The empirical results show that this method is effective in the multiclass setting as well. We further show that the path-based information source always contributes to the classification, and analyze the cases in which it mostly complements the distributional information.
Anthology ID:
W16-5304
Volume:
Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V)
Month:
December
Year:
2016
Address:
Osaka, Japan
Venues:
CogALex | WS
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
24–29
Language:
URL:
https://aclanthology.org/W16-5304
DOI:
Bibkey:
Cite (ACL):
Vered Shwartz and Ido Dagan. 2016. Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations. In Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V), pages 24–29, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations (Shwartz & Dagan, 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-5304.pdf
Code
 vered1986/LexNET