@inproceedings{dyer-etal-2024-multilingual,
title = "A Multilingual Parallel Corpus for Coreference Resolution and Information Status in the Literary Domain",
author = "Dyer, Andrew and
Betul Bahceci, Ruveyda and
Rajestari, Maryam and
Rouvalis, Andreas and
Singhal, Aarushi and
Stodolinska, Yuliya and
Asma Umniyati, Syahidah and
Rodrigues Menezes de Oliveira Vaz, Helena",
editor = {Dakota, Daniel and
Jablotschkin, Sarah and
K{\"u}bler, Sandra and
Zinsmeister, Heike},
booktitle = "Proceedings of the 22nd Workshop on Treebanks and Linguistic Theories (TLT 2024)",
month = dec,
year = "2024",
address = "Hamburg,Germany",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.tlt-1.7/",
pages = "55--64",
abstract = "Information status {---} the newness or givenness of referents in discourse {---} is known to affect the production of language at many different levels. At the morphosyntactic level, information status gives rise to special words orders, elisions, and other phenomena that challenge the notion that morphosyntax can be considered independent of discourse context. Though there are many language-specific corpora annotated for information status and its related phenomena, coreference and anaphora resolution, what is not available at present is a cross-lingually consistently annotated corpus or annotation scheme that would allow for comparativestudy of these phenomena across many diverse languages. In this paper we present our work to build such a resource. We are annotating a parsed, parallel corpus of prose in many languages for information status and coreference resolution, so that like-for-like cross-lingual comparisons can be made at the intersection of discourse and syntax. Our corpus can and will be used bot"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dyer-etal-2024-multilingual">
<titleInfo>
<title>A Multilingual Parallel Corpus for Coreference Resolution and Information Status in the Literary Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruveyda</namePart>
<namePart type="family">Betul Bahceci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Rajestari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Rouvalis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aarushi</namePart>
<namePart type="family">Singhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuliya</namePart>
<namePart type="family">Stodolinska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syahidah</namePart>
<namePart type="family">Asma Umniyati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Rodrigues Menezes de Oliveira Vaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Workshop on Treebanks and Linguistic Theories (TLT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Dakota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Jablotschkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Zinsmeister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hamburg,Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Information status — the newness or givenness of referents in discourse — is known to affect the production of language at many different levels. At the morphosyntactic level, information status gives rise to special words orders, elisions, and other phenomena that challenge the notion that morphosyntax can be considered independent of discourse context. Though there are many language-specific corpora annotated for information status and its related phenomena, coreference and anaphora resolution, what is not available at present is a cross-lingually consistently annotated corpus or annotation scheme that would allow for comparativestudy of these phenomena across many diverse languages. In this paper we present our work to build such a resource. We are annotating a parsed, parallel corpus of prose in many languages for information status and coreference resolution, so that like-for-like cross-lingual comparisons can be made at the intersection of discourse and syntax. Our corpus can and will be used bot</abstract>
<identifier type="citekey">dyer-etal-2024-multilingual</identifier>
<location>
<url>https://aclanthology.org/2024.tlt-1.7/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>55</start>
<end>64</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multilingual Parallel Corpus for Coreference Resolution and Information Status in the Literary Domain
%A Dyer, Andrew
%A Betul Bahceci, Ruveyda
%A Rajestari, Maryam
%A Rouvalis, Andreas
%A Singhal, Aarushi
%A Stodolinska, Yuliya
%A Asma Umniyati, Syahidah
%A Rodrigues Menezes de Oliveira Vaz, Helena
%Y Dakota, Daniel
%Y Jablotschkin, Sarah
%Y Kübler, Sandra
%Y Zinsmeister, Heike
%S Proceedings of the 22nd Workshop on Treebanks and Linguistic Theories (TLT 2024)
%D 2024
%8 December
%I Association for Computational Linguistics
%C Hamburg,Germany
%F dyer-etal-2024-multilingual
%X Information status — the newness or givenness of referents in discourse — is known to affect the production of language at many different levels. At the morphosyntactic level, information status gives rise to special words orders, elisions, and other phenomena that challenge the notion that morphosyntax can be considered independent of discourse context. Though there are many language-specific corpora annotated for information status and its related phenomena, coreference and anaphora resolution, what is not available at present is a cross-lingually consistently annotated corpus or annotation scheme that would allow for comparativestudy of these phenomena across many diverse languages. In this paper we present our work to build such a resource. We are annotating a parsed, parallel corpus of prose in many languages for information status and coreference resolution, so that like-for-like cross-lingual comparisons can be made at the intersection of discourse and syntax. Our corpus can and will be used bot
%U https://aclanthology.org/2024.tlt-1.7/
%P 55-64
Markdown (Informal)
[A Multilingual Parallel Corpus for Coreference Resolution and Information Status in the Literary Domain](https://aclanthology.org/2024.tlt-1.7/) (Dyer et al., TLT 2024)
ACL
- Andrew Dyer, Ruveyda Betul Bahceci, Maryam Rajestari, Andreas Rouvalis, Aarushi Singhal, Yuliya Stodolinska, Syahidah Asma Umniyati, and Helena Rodrigues Menezes de Oliveira Vaz. 2024. A Multilingual Parallel Corpus for Coreference Resolution and Information Status in the Literary Domain. In Proceedings of the 22nd Workshop on Treebanks and Linguistic Theories (TLT 2024), pages 55–64, Hamburg,Germany. Association for Computational Linguistics.