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

Conference contribution
(Conference Contribution)


Publication Details

Author(s): Evert S
Publishing place: Osaka, Japan
Publication year: 2016
Conference Proceedings Title: Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex-V)
Pages range: 92-97
Language: English


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.



FAU Authors / FAU Editors

Evert, Stefan Prof. Dr.
Lehrstuhl für Korpus- und Computerlinguistik


Research Fields

Collocations, multiword expressions and corpus-based discourse analysis
Lehrstuhl für Korpus- und Computerlinguistik


How to cite

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, Stefan. "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: 

Last updated on 2018-11-08 at 00:09