Proceedings chapter
Open access

Predictability of Distributional Semantics in Derivational Word Formation

Presented at Osaka (Japan), 11-17 December 2016
Publication date2016

Compositional distributional semantic models (CDSMs) have successfully been applied to the task of predicting the meaning of a range of linguistic constructions. Their performance on semi-compositional word formation process of (morphological) derivation, however, has been extremely variable, with no large-scale empirical investigation to date. This paper fills that gap, performing an analysis of CDSM predictions on a large dataset (over 30,000 German derivationally related word pairs). We use linear regression models to analyze CDSM performance and obtain insights into the linguistic factors that influence how predictable the distributional context of a derived word is going to be. We identify various such factors, notably part of speech, argument structure, and semantic regularity.

Citation (ISO format)
PADÓ, Sebastian et al. Predictability of Distributional Semantics in Derivational Word Formation. In: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics : Technical Papers. Osaka (Japan). [s.l.] : [s.n.], 2016. p. 1285–1296.
Main files (1)
Proceedings chapter (Published version)
  • PID : unige:139494

Technical informations

Creation07/30/2020 5:36:00 PM
First validation07/30/2020 5:36:00 PM
Update time03/15/2023 10:24:55 PM
Status update03/15/2023 10:24:54 PM
Last indexation08/30/2023 11:18:38 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack