We report on a study applying compositional distributional semantic models (CDSMs) to a set of Ukrainian derivational patterns. Ukrainian is an interesting language as it is morphologically rich, and low-resource. Our study aims at resolving inconsistent results from previous studies which employed CDSMs for derivation; we provide evidence for a cross-lingual advantage of CBOW over NMF representations, as well as a simple additive over a lexical function model. In addition, we present two case studies in which we test the capabilities of CDSMs to deal with pattern-level ambiguity and apply the same CDSMs to inflectional patterns.
%0 Conference Paper
%1 melymuka17:_model_deriv_morph_in_ukrain
%A Melymuka, Mariia
%A Lapesa, Gabriella
%A Kisselew, Max
%A Padó, Sebastian
%B Proceedings of IWCS
%C Montpellier, France
%D 2017
%K conference myown
%T Modeling Derivational Morphology in Ukrainian
%U http://aclweb.org/anthology/W/W17/W17-6928.pdf
%X We report on a study applying compositional distributional semantic models (CDSMs) to a set of Ukrainian derivational patterns. Ukrainian is an interesting language as it is morphologically rich, and low-resource. Our study aims at resolving inconsistent results from previous studies which employed CDSMs for derivation; we provide evidence for a cross-lingual advantage of CBOW over NMF representations, as well as a simple additive over a lexical function model. In addition, we present two case studies in which we test the capabilities of CDSMs to deal with pattern-level ambiguity and apply the same CDSMs to inflectional patterns.
@inproceedings{melymuka17:_model_deriv_morph_in_ukrain,
abstract = {We report on a study applying compositional distributional semantic models (CDSMs) to a set of Ukrainian derivational patterns. Ukrainian is an interesting language as it is morphologically rich, and low-resource. Our study aims at resolving inconsistent results from previous studies which employed CDSMs for derivation; we provide evidence for a cross-lingual advantage of CBOW over NMF representations, as well as a simple additive over a lexical function model. In addition, we present two case studies in which we test the capabilities of CDSMs to deal with pattern-level ambiguity and apply the same CDSMs to inflectional patterns.},
added-at = {2017-07-14T21:42:12.000+0200},
address = {Montpellier, France},
author = {Melymuka, Mariia and Lapesa, Gabriella and Kisselew, Max and Padó, Sebastian},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2e1c0c3e5f10767fe98a386ca1a68b606/sp},
booktitle = {Proceedings of IWCS},
interhash = {0422c93a19170a0b70d3b96e12f3ec33},
intrahash = {e1c0c3e5f10767fe98a386ca1a68b606},
keywords = {conference myown},
timestamp = {2017-10-27T15:50:55.000+0200},
title = {Modeling Derivational Morphology in {U}krainian},
url = {http://aclweb.org/anthology/W/W17/W17-6928.pdf},
year = 2017
}
