S. Pado and A. Herbelot and M. Kisselew and J. Šnajder. Predictability of Distributional Semantics in Derivational Word Formation. Proceedings of COLING 2016, Osaka, Japan.
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.
@InProceedings{pado16:_predic_distr_seman_deriv_word_format,
author = {Sebastian Padó and Aurélie Herbelot and Max Kisselew
and Jan \v{S}najder},
title = {Predictability of Distributional Semantics
in Derivational Word Formation},
booktitle = {Proceedings of COLING},
year = 2016,
address = {Osaka, Japan},
pages = {1285--1296}