@inproceedings{puzyrev-etal-2019-dataset,
title = "A Dataset for Noun Compositionality Detection for a {S}lavic Language",
author = "Puzyrev, Dmitry and
Shelmanov, Artem and
Panchenko, Alexander and
Artemova, Ekaterina",
editor = "Erjavec, Toma{\v{z}} and
Marci{\'n}czuk, Micha{\l} and
Nakov, Preslav and
Piskorski, Jakub and
Pivovarova, Lidia and
{\v{S}}najder, Jan and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3708",
doi = "10.18653/v1/W19-3708",
pages = "56--62",
abstract = "This paper presents the first gold-standard resource for Russian annotated with compositionality information of noun compounds. The compound phrases are collected from the Universal Dependency treebanks according to part of speech patterns, such as ADJ+NOUN or NOUN+NOUN, using the gold-standard annotations. Each compound phrase is annotated by two experts and a moderator according to the following schema: the phrase can be either compositional, non-compositional, or ambiguous (i.e., depending on the context it can be interpreted both as compositional or non-compositional). We conduct an experimental evaluation of models and methods for predicting compositionality of noun compounds in unsupervised and supervised setups. We show that methods from previous work evaluated on the proposed Russian-language resource achieve the performance comparable with results on English corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="puzyrev-etal-2019-dataset">
<titleInfo>
<title>A Dataset for Noun Compositionality Detection for a Slavic Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dmitry</namePart>
<namePart type="family">Puzyrev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Panchenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Artemova</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 7th Workshop on Balto-Slavic Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Marcińczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</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 the first gold-standard resource for Russian annotated with compositionality information of noun compounds. The compound phrases are collected from the Universal Dependency treebanks according to part of speech patterns, such as ADJ+NOUN or NOUN+NOUN, using the gold-standard annotations. Each compound phrase is annotated by two experts and a moderator according to the following schema: the phrase can be either compositional, non-compositional, or ambiguous (i.e., depending on the context it can be interpreted both as compositional or non-compositional). We conduct an experimental evaluation of models and methods for predicting compositionality of noun compounds in unsupervised and supervised setups. We show that methods from previous work evaluated on the proposed Russian-language resource achieve the performance comparable with results on English corpora.</abstract>
<identifier type="citekey">puzyrev-etal-2019-dataset</identifier>
<identifier type="doi">10.18653/v1/W19-3708</identifier>
<location>
<url>https://aclanthology.org/W19-3708</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>56</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Dataset for Noun Compositionality Detection for a Slavic Language
%A Puzyrev, Dmitry
%A Shelmanov, Artem
%A Panchenko, Alexander
%A Artemova, Ekaterina
%Y Erjavec, Tomaž
%Y Marcińczuk, Michał
%Y Nakov, Preslav
%Y Piskorski, Jakub
%Y Pivovarova, Lidia
%Y Šnajder, Jan
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F puzyrev-etal-2019-dataset
%X This paper presents the first gold-standard resource for Russian annotated with compositionality information of noun compounds. The compound phrases are collected from the Universal Dependency treebanks according to part of speech patterns, such as ADJ+NOUN or NOUN+NOUN, using the gold-standard annotations. Each compound phrase is annotated by two experts and a moderator according to the following schema: the phrase can be either compositional, non-compositional, or ambiguous (i.e., depending on the context it can be interpreted both as compositional or non-compositional). We conduct an experimental evaluation of models and methods for predicting compositionality of noun compounds in unsupervised and supervised setups. We show that methods from previous work evaluated on the proposed Russian-language resource achieve the performance comparable with results on English corpora.
%R 10.18653/v1/W19-3708
%U https://aclanthology.org/W19-3708
%U https://doi.org/10.18653/v1/W19-3708
%P 56-62
Markdown (Informal)
[A Dataset for Noun Compositionality Detection for a Slavic Language](https://aclanthology.org/W19-3708) (Puzyrev et al., BSNLP 2019)
ACL