Evert S (2016)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2016
City/Town: Osaka, Japan
Pages Range: 92-97
Conference Proceedings Title: Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex-V)
URI: http://www.collocations.de/data/#mach5
Open Access Link: http://aclweb.org/anthology/W16-5312
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.
APA:
Evert, S. (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) (pp. 92-97). Osaka, Japan.
MLA:
Evert, Stephanie. "CogALex-V Shared Task: Mach5 – A traditional DSM approach to semantic relatedness." Proceedings of the Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex-V) Osaka, Japan, 2016. 92-97.
BibTeX: Download