TY - GEN
T1 - When Polysemy Matters
T2 - 11th Joint Conference on Lexical and Computational Semantics, StarSEM 2022
AU - Soper, Elizabeth
AU - Koenig, Jean Pierre
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - Recent work using word embeddings to model semantic categorization have indicated that static models outperform the more recent contextual class of models (Majewska et al., 2021). In this paper, we consider polysemy as a possible confounding factor, comparing sense-level embeddings with previously studied static embeddings on both coarse- and fine-grained categorization tasks. We find that the effect of polysemy depends on how one defines semantic categorization; while sense-level embeddings dramatically outperform static embeddings in predicting coarse-grained categories derived from a word sorting task, they perform approximately equally in predicting fine-grained categories derived from context-free similarity judgments. Our findings highlight the different processes underlying human behavior on different types of semantic tasks.
AB - Recent work using word embeddings to model semantic categorization have indicated that static models outperform the more recent contextual class of models (Majewska et al., 2021). In this paper, we consider polysemy as a possible confounding factor, comparing sense-level embeddings with previously studied static embeddings on both coarse- and fine-grained categorization tasks. We find that the effect of polysemy depends on how one defines semantic categorization; while sense-level embeddings dramatically outperform static embeddings in predicting coarse-grained categories derived from a word sorting task, they perform approximately equally in predicting fine-grained categories derived from context-free similarity judgments. Our findings highlight the different processes underlying human behavior on different types of semantic tasks.
UR - https://www.scopus.com/pages/publications/85139167740
M3 - Conference contribution
AN - SCOPUS:85139167740
T3 - *SEM 2022 - 11th Joint Conference on Lexical and Computational Semantics, Proceedings of the Conference
SP - 123
EP - 131
BT - *SEM 2022 - 11th Joint Conference on Lexical and Computational Semantics, Proceedings of the Conference
A2 - Nastase, Vivi
A2 - Pavlick, Ellie
A2 - Pilehvar, Mohammad Taher
A2 - Camacho-Collados, Jose
A2 - Raganato, Alessandro
PB - Association for Computational Linguistics (ACL)
Y2 - 14 July 2022 through 15 July 2022
ER -