Jean-Pierre Koenig

Also published as: Jean-pierre Koenig


When Polysemy Matters: Modeling Semantic Categorization with Word Embeddings
Elizabeth Soper | Jean-pierre Koenig
Proceedings of the 11th Joint Conference on Lexical and Computational Semantics

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.


Event Categorization beyond Verb Senses
Aron Marvel | Jean-Pierre Koenig
Proceedings of the 11th Workshop on Multiword Expressions


Book Reviews: Head-driven Phrase Structure Grammar and German in Head-driven Phrase-structure Grammar
Jean-Pierre Koenig
Computational Linguistics, Volume 22, Number 1, March 1996