@inproceedings{novak-etal-2020-cbow,
title = "{CBOW}-tag: a Modified {CBOW} Algorithm for Generating Embedding Models from Annotated Corpora",
author = "Nov{\'a}k, Attila and
Laki, L{\'a}szl{\'o} and
Nov{\'a}k, Borb{\'a}la",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.590",
pages = "4798--4801",
abstract = "In this paper, we present a modified version of the CBOW algorithm implemented in the fastText framework. Our modified algorithm, CBOW-tag builds a vector space model that includes the representation of the original word forms and their annotation at the same time. We illustrate the results by presenting a model built from a corpus that includes morphological and syntactic annotations. The simultaneous presence of unannotated elements and different annotations at the same time in the model makes it possible to constrain nearest neighbour queries to specific types of elements. The model can thus efficiently answer questions such as What do we eat?, What can we do with a skeleton? What else do we do with what we eat?, etc. Error analysis reveals that the model can highlight errors introduced into the annotation by the tagger and parser we used to generate the annotations as well as lexical peculiarities in the corpus itself, especially if we do not limit the vocabulary of the model to frequent items.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="novak-etal-2020-cbow">
<titleInfo>
<title>CBOW-tag: a Modified CBOW Algorithm for Generating Embedding Models from Annotated Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Attila</namePart>
<namePart type="family">Novák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">László</namePart>
<namePart type="family">Laki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Borbála</namePart>
<namePart type="family">Novák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this paper, we present a modified version of the CBOW algorithm implemented in the fastText framework. Our modified algorithm, CBOW-tag builds a vector space model that includes the representation of the original word forms and their annotation at the same time. We illustrate the results by presenting a model built from a corpus that includes morphological and syntactic annotations. The simultaneous presence of unannotated elements and different annotations at the same time in the model makes it possible to constrain nearest neighbour queries to specific types of elements. The model can thus efficiently answer questions such as What do we eat?, What can we do with a skeleton? What else do we do with what we eat?, etc. Error analysis reveals that the model can highlight errors introduced into the annotation by the tagger and parser we used to generate the annotations as well as lexical peculiarities in the corpus itself, especially if we do not limit the vocabulary of the model to frequent items.</abstract>
<identifier type="citekey">novak-etal-2020-cbow</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.590</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4798</start>
<end>4801</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CBOW-tag: a Modified CBOW Algorithm for Generating Embedding Models from Annotated Corpora
%A Novák, Attila
%A Laki, László
%A Novák, Borbála
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F novak-etal-2020-cbow
%X In this paper, we present a modified version of the CBOW algorithm implemented in the fastText framework. Our modified algorithm, CBOW-tag builds a vector space model that includes the representation of the original word forms and their annotation at the same time. We illustrate the results by presenting a model built from a corpus that includes morphological and syntactic annotations. The simultaneous presence of unannotated elements and different annotations at the same time in the model makes it possible to constrain nearest neighbour queries to specific types of elements. The model can thus efficiently answer questions such as What do we eat?, What can we do with a skeleton? What else do we do with what we eat?, etc. Error analysis reveals that the model can highlight errors introduced into the annotation by the tagger and parser we used to generate the annotations as well as lexical peculiarities in the corpus itself, especially if we do not limit the vocabulary of the model to frequent items.
%U https://aclanthology.org/2020.lrec-1.590
%P 4798-4801
Markdown (Informal)
[CBOW-tag: a Modified CBOW Algorithm for Generating Embedding Models from Annotated Corpora](https://aclanthology.org/2020.lrec-1.590) (Novák et al., LREC 2020)
ACL