@inproceedings{ehren-2017-literal,
title = "Literal or idiomatic? Identifying the reading of single occurrences of {G}erman multiword expressions using word embeddings",
author = "Ehren, Rafael",
editor = "Kunneman, Florian and
I{\~n}urrieta, Uxoa and
Camilleri, John J. and
Ardanuy, Mariona Coll",
booktitle = "Proceedings of the Student Research Workshop at the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-4011/",
pages = "103--112",
abstract = "Non-compositional multiword expressions (MWEs) still pose serious issues for a variety of natural language processing tasks and their ubiquity makes it impossible to get around methods which automatically identify these kind of MWEs. The method presented in this paper was inspired by Sporleder and Li (2009) and is able to discriminate between the literal and non-literal use of an MWE in an unsupervised way. It is based on the assumption that words in a text form cohesive units. If the cohesion of these units is weakened by an expression, it is classified as literal, and otherwise as idiomatic. While Sporleder an Li used \textit{Normalized Google Distance} to modell semantic similarity, the present work examines the use of a variety of different word embeddings."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ehren-2017-literal">
<titleInfo>
<title>Literal or idiomatic? Identifying the reading of single occurrences of German multiword expressions using word embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Ehren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Kunneman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Uxoa</namePart>
<namePart type="family">Iñurrieta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Camilleri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariona</namePart>
<namePart type="given">Coll</namePart>
<namePart type="family">Ardanuy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Non-compositional multiword expressions (MWEs) still pose serious issues for a variety of natural language processing tasks and their ubiquity makes it impossible to get around methods which automatically identify these kind of MWEs. The method presented in this paper was inspired by Sporleder and Li (2009) and is able to discriminate between the literal and non-literal use of an MWE in an unsupervised way. It is based on the assumption that words in a text form cohesive units. If the cohesion of these units is weakened by an expression, it is classified as literal, and otherwise as idiomatic. While Sporleder an Li used Normalized Google Distance to modell semantic similarity, the present work examines the use of a variety of different word embeddings.</abstract>
<identifier type="citekey">ehren-2017-literal</identifier>
<location>
<url>https://aclanthology.org/E17-4011/</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>103</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Literal or idiomatic? Identifying the reading of single occurrences of German multiword expressions using word embeddings
%A Ehren, Rafael
%Y Kunneman, Florian
%Y Iñurrieta, Uxoa
%Y Camilleri, John J.
%Y Ardanuy, Mariona Coll
%S Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F ehren-2017-literal
%X Non-compositional multiword expressions (MWEs) still pose serious issues for a variety of natural language processing tasks and their ubiquity makes it impossible to get around methods which automatically identify these kind of MWEs. The method presented in this paper was inspired by Sporleder and Li (2009) and is able to discriminate between the literal and non-literal use of an MWE in an unsupervised way. It is based on the assumption that words in a text form cohesive units. If the cohesion of these units is weakened by an expression, it is classified as literal, and otherwise as idiomatic. While Sporleder an Li used Normalized Google Distance to modell semantic similarity, the present work examines the use of a variety of different word embeddings.
%U https://aclanthology.org/E17-4011/
%P 103-112
Markdown (Informal)
[Literal or idiomatic? Identifying the reading of single occurrences of German multiword expressions using word embeddings](https://aclanthology.org/E17-4011/) (Ehren, EACL 2017)
ACL