CogALex-V Shared Task: Mach5 – A traditional DSM approach to semantic relatedness

Stefan Evert


Abstract
This contribution provides a strong baseline result for the CogALex-V shared task using a traditional “count”-type DSM (placed in rank 2 out of 7 in subtask 1 and rank 3 out of 6 in subtask 2). Parameter tuning experiments reveal some surprising effects and suggest that the use of random word pairs as negative examples may be problematic, guiding the parameter optimization in an undesirable direction.
Anthology ID:
W16-5312
Volume:
Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V)
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Michael Zock, Alessandro Lenci, Stefan Evert
Venue:
CogALex
SIG:
SIGLEX
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
92–97
Language:
URL:
https://aclanthology.org/W16-5312
DOI:
Bibkey:
Cite (ACL):
Stefan Evert. 2016. CogALex-V Shared Task: Mach5 – A traditional DSM approach to semantic relatedness. In Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex - V), pages 92–97, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
CogALex-V Shared Task: Mach5 – A traditional DSM approach to semantic relatedness (Evert, CogALex 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-5312.pdf