@inproceedings{chiarcos-2022-inducing,
title = "Inducing Discourse Marker Inventories from Lexical Knowledge Graphs",
author = "Chiarcos, Christian",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.257",
pages = "2401--2412",
abstract = "Discourse marker inventories are important tools for the development of both discourse parsers and corpora with discourse annotations. In this paper we explore the potential of massively multilingual lexical knowledge graphs to induce multilingual discourse marker lexicons using concept propagation methods as previously developed in the context of translation inference across dictionaries. Given one or multiple source languages with discourse marker inventories that discourse relations as senses of potential discourse markers, as well as a large number of bilingual dictionaries that link them {--} directly or indirectly {--} with the target language, we specifically study to what extent discourse marker induction can benefit from the integration of information from different sources, the impact of sense granularity and what limiting factors may need to be considered. Our study uses discourse marker inventories from nine European languages normalized against the discourse relation inventory of the Penn Discourse Treebank (PDTB), as well as three collections of machine-readable dictionaries with different characteristics, so that the interplay of a large number of factors can be studied.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chiarcos-2022-inducing">
<titleInfo>
<title>Inducing Discourse Marker Inventories from Lexical Knowledge Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Chiarcos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>Discourse marker inventories are important tools for the development of both discourse parsers and corpora with discourse annotations. In this paper we explore the potential of massively multilingual lexical knowledge graphs to induce multilingual discourse marker lexicons using concept propagation methods as previously developed in the context of translation inference across dictionaries. Given one or multiple source languages with discourse marker inventories that discourse relations as senses of potential discourse markers, as well as a large number of bilingual dictionaries that link them – directly or indirectly – with the target language, we specifically study to what extent discourse marker induction can benefit from the integration of information from different sources, the impact of sense granularity and what limiting factors may need to be considered. Our study uses discourse marker inventories from nine European languages normalized against the discourse relation inventory of the Penn Discourse Treebank (PDTB), as well as three collections of machine-readable dictionaries with different characteristics, so that the interplay of a large number of factors can be studied.</abstract>
<identifier type="citekey">chiarcos-2022-inducing</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.257</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2401</start>
<end>2412</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inducing Discourse Marker Inventories from Lexical Knowledge Graphs
%A Chiarcos, Christian
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F chiarcos-2022-inducing
%X Discourse marker inventories are important tools for the development of both discourse parsers and corpora with discourse annotations. In this paper we explore the potential of massively multilingual lexical knowledge graphs to induce multilingual discourse marker lexicons using concept propagation methods as previously developed in the context of translation inference across dictionaries. Given one or multiple source languages with discourse marker inventories that discourse relations as senses of potential discourse markers, as well as a large number of bilingual dictionaries that link them – directly or indirectly – with the target language, we specifically study to what extent discourse marker induction can benefit from the integration of information from different sources, the impact of sense granularity and what limiting factors may need to be considered. Our study uses discourse marker inventories from nine European languages normalized against the discourse relation inventory of the Penn Discourse Treebank (PDTB), as well as three collections of machine-readable dictionaries with different characteristics, so that the interplay of a large number of factors can be studied.
%U https://aclanthology.org/2022.lrec-1.257
%P 2401-2412
Markdown (Informal)
[Inducing Discourse Marker Inventories from Lexical Knowledge Graphs](https://aclanthology.org/2022.lrec-1.257) (Chiarcos, LREC 2022)
ACL