@inproceedings{garcia-etal-2019-comparison,
title = "A comparison of statistical association measures for identifying dependency-based collocations in various languages.",
author = "Garcia, Marcos and
Garc{\'\i}a Salido, Marcos and
Alonso-Ramos, Margarita",
editor = "Savary, Agata and
Escart{\'\i}n, Carla Parra and
Bond, Francis and
Mitrovi{\'c}, Jelena and
Mititelu, Verginica Barbu",
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5107",
doi = "10.18653/v1/W19-5107",
pages = "49--59",
abstract = "This paper presents an exploration of different statistical association measures to automatically identify collocations from corpora in English, Portuguese, and Spanish. To evaluate the impact of the association metrics we manually annotated corpora with three different syntactic patterns of collocations (adjective-noun, verb-object and nominal compounds). We took advantage of the PARSEME 1.1 Shared Task corpora by selecting a subset of 155k tokens in the three referred languages, in which we annotated 1,526 collocations with the corresponding Lexical Functions according to the Meaning-Text Theory. Using the resulting gold-standard, we have carried out a comparison between frequency data and several well-known association measures, both symmetric and asymmetric. The results show that the combination of dependency triples with raw frequency information is as powerful as the best association measures in most syntactic patterns and languages. Furthermore, and despite the asymmetric behaviour of collocations, directional approaches perform worse than the symmetric ones in the extraction of these phraseological combinations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-etal-2019-comparison">
<titleInfo>
<title>A comparison of statistical association measures for identifying dependency-based collocations in various languages.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">García Salido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margarita</namePart>
<namePart type="family">Alonso-Ramos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelena</namePart>
<namePart type="family">Mitrović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents an exploration of different statistical association measures to automatically identify collocations from corpora in English, Portuguese, and Spanish. To evaluate the impact of the association metrics we manually annotated corpora with three different syntactic patterns of collocations (adjective-noun, verb-object and nominal compounds). We took advantage of the PARSEME 1.1 Shared Task corpora by selecting a subset of 155k tokens in the three referred languages, in which we annotated 1,526 collocations with the corresponding Lexical Functions according to the Meaning-Text Theory. Using the resulting gold-standard, we have carried out a comparison between frequency data and several well-known association measures, both symmetric and asymmetric. The results show that the combination of dependency triples with raw frequency information is as powerful as the best association measures in most syntactic patterns and languages. Furthermore, and despite the asymmetric behaviour of collocations, directional approaches perform worse than the symmetric ones in the extraction of these phraseological combinations.</abstract>
<identifier type="citekey">garcia-etal-2019-comparison</identifier>
<identifier type="doi">10.18653/v1/W19-5107</identifier>
<location>
<url>https://aclanthology.org/W19-5107</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>49</start>
<end>59</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A comparison of statistical association measures for identifying dependency-based collocations in various languages.
%A Garcia, Marcos
%A García Salido, Marcos
%A Alonso-Ramos, Margarita
%Y Savary, Agata
%Y Escartín, Carla Parra
%Y Bond, Francis
%Y Mitrović, Jelena
%Y Mititelu, Verginica Barbu
%S Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F garcia-etal-2019-comparison
%X This paper presents an exploration of different statistical association measures to automatically identify collocations from corpora in English, Portuguese, and Spanish. To evaluate the impact of the association metrics we manually annotated corpora with three different syntactic patterns of collocations (adjective-noun, verb-object and nominal compounds). We took advantage of the PARSEME 1.1 Shared Task corpora by selecting a subset of 155k tokens in the three referred languages, in which we annotated 1,526 collocations with the corresponding Lexical Functions according to the Meaning-Text Theory. Using the resulting gold-standard, we have carried out a comparison between frequency data and several well-known association measures, both symmetric and asymmetric. The results show that the combination of dependency triples with raw frequency information is as powerful as the best association measures in most syntactic patterns and languages. Furthermore, and despite the asymmetric behaviour of collocations, directional approaches perform worse than the symmetric ones in the extraction of these phraseological combinations.
%R 10.18653/v1/W19-5107
%U https://aclanthology.org/W19-5107
%U https://doi.org/10.18653/v1/W19-5107
%P 49-59
Markdown (Informal)
[A comparison of statistical association measures for identifying dependency-based collocations in various languages.](https://aclanthology.org/W19-5107) (Garcia et al., MWE 2019)
ACL