Detection of Semantic Compositionality using Semantic Spaces

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F12%3A43915977" target="_blank" >RIV/49777513:23520/12:43915977 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-642-32790-2_43" target="_blank" >http://dx.doi.org/10.1007/978-3-642-32790-2_43</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-642-32790-2_43" target="_blank" >10.1007/978-3-642-32790-2_43</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Detection of Semantic Compositionality using Semantic Spaces

Popis výsledku v původním jazyce

Any Natural Language Processing (NLP) system that does semantic processing relies on the assumption of semantic compositionality: the meaning of a compound is determined by the meaning of its parts and their combination. However, the compositionality assumption does not hold for many idiomatic expressions such as "blue chip". This paper focuses on the fully automatic detection of these, further referred to as non-compositional compounds. We have proposed and tested an intuitive approach based on replacing the parts of compounds by semantically related words. Our models determining the compositionality combine simple statistic ideas with the COALS semantic space. For the evaluation, the shared dataset for the Distributional Semantics and Compositionality 2011 workshop (DISCO 2011) is used. A comparison of our approach with the traditionally used Pointwise Mutual Information (PMI) is also presented. Our best models outperform all the systems competing in DISCO 2011.

Název v anglickém jazyce

Detection of Semantic Compositionality using Semantic Spaces

Popis výsledku anglicky

Any Natural Language Processing (NLP) system that does semantic processing relies on the assumption of semantic compositionality: the meaning of a compound is determined by the meaning of its parts and their combination. However, the compositionality assumption does not hold for many idiomatic expressions such as "blue chip". This paper focuses on the fully automatic detection of these, further referred to as non-compositional compounds. We have proposed and tested an intuitive approach based on replacing the parts of compounds by semantically related words. Our models determining the compositionality combine simple statistic ideas with the COALS semantic space. For the evaluation, the shared dataset for the Distributional Semantics and Compositionality 2011 workshop (DISCO 2011) is used. A comparison of our approach with the traditionally used Pointwise Mutual Information (PMI) is also presented. Our best models outperform all the systems competing in DISCO 2011.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2012

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

TSD 2012

ISBN

978-3-642-32789-6

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

353-361

Název nakladatele

Springer

Místo vydání

Heidelberg

Místo konání akce

Brno

Datum konání akce

3. 9. 2012

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—