Kvistur: Vélræn stofnhlutagreining samsettra orða
Orð og tunga · 2015
DOI: 10.33112/ordogtunga.17.7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Orð og tunga, 2015. Verfasst von Jón Friðrik Daðason und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Compounding is extremely productive in Icelandic and multi-word compounds are common. The likelihood of finding previously unseen compounds in texts is thus very high, which makes out-of-vocabulary words a problem in the use of NLP tools. Kvistur, the decompounder described in this paper, splits Icelandic compounds and shows their binary constituent structure. The probability of a constituent in an unknown (or unanalysed) compound forming a combined constituent with either of its neighbours is estimated, with the use of data on the constituent structure of over 240 thousand compounds from the Database of Modern Icelandic Inflection (Kristín Bjarna-dótt ir 2012), and word frequencies from Íslenskur orðasjóður, a corpus of approx. 550 million words. Thus, the structure of an unknown compound is derived by comparison with compounds with partially the same constituents and similar structure in the training data. The granularity of the split returned by the decompounder is important in tasks such as semantic analysis or machine translation, where a fl at (non-structured) sequence of constituents is insufficient.
Zitieren
APA
Daðason, J. F., & Bjarnadóttir, K. (2015). Kvistur: Vélræn stofnhlutagreining samsettra orða. Orð og tunga. https://doi.org/10.33112/ordogtunga.17.7
Vancouver
Daðason JF, Bjarnadóttir K. Kvistur: Vélræn stofnhlutagreining samsettra orða. Orð og tunga. 2015. doi:10.33112/ordogtunga.17.7
BibTeX
@article{Daason2015,
author = {Daðason, Jón Friðrik and Bjarnadóttir, Kristín},
title = {Kvistur: Vélræn stofnhlutagreining samsettra orða},
journal = {Orð og tunga},
year = {2015},
doi = {10.33112/ordogtunga.17.7}
}
EUVIMED