@inproceedings{popel-etal-2021-ud-trees,
title = "Do {UD} Trees Match Mention Spans in Coreference Annotations?",
author = "Popel, Martin and
{\v{Z}}abokrtsk{\'y}, Zden{\v{e}}k and
Nedoluzhko, Anna and
Nov{\'a}k, Michal and
Zeman, Daniel",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.303",
doi = "10.18653/v1/2021.findings-emnlp.303",
pages = "3570--3576",
abstract = "One can find dozens of data resources for various languages in which coreference - a relation between two or more expressions that refer to the same real-world entity - is manually annotated. One could also assume that such expressions usually constitute syntactically meaningful units; however, mention spans have been annotated simply by delimiting token intervals in most coreference projects, i.e., independently of any syntactic representation. We argue that it could be advantageous to make syntactic and coreference annotations convergent in the long term. We present a pilot empirical study focused on matches and mismatches between hand-annotated linear mention spans and automatically parsed syntactic trees that follow Universal Dependencies conventions. The study covers 9 datasets for 8 different languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="popel-etal-2021-ud-trees">
<titleInfo>
<title>Do UD Trees Match Mention Spans in Coreference Annotations?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Popel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zdeněk</namePart>
<namePart type="family">Žabokrtský</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Nedoluzhko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Novák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Zeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One can find dozens of data resources for various languages in which coreference - a relation between two or more expressions that refer to the same real-world entity - is manually annotated. One could also assume that such expressions usually constitute syntactically meaningful units; however, mention spans have been annotated simply by delimiting token intervals in most coreference projects, i.e., independently of any syntactic representation. We argue that it could be advantageous to make syntactic and coreference annotations convergent in the long term. We present a pilot empirical study focused on matches and mismatches between hand-annotated linear mention spans and automatically parsed syntactic trees that follow Universal Dependencies conventions. The study covers 9 datasets for 8 different languages.</abstract>
<identifier type="citekey">popel-etal-2021-ud-trees</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.303</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.303</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3570</start>
<end>3576</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do UD Trees Match Mention Spans in Coreference Annotations?
%A Popel, Martin
%A Žabokrtský, Zdeněk
%A Nedoluzhko, Anna
%A Novák, Michal
%A Zeman, Daniel
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F popel-etal-2021-ud-trees
%X One can find dozens of data resources for various languages in which coreference - a relation between two or more expressions that refer to the same real-world entity - is manually annotated. One could also assume that such expressions usually constitute syntactically meaningful units; however, mention spans have been annotated simply by delimiting token intervals in most coreference projects, i.e., independently of any syntactic representation. We argue that it could be advantageous to make syntactic and coreference annotations convergent in the long term. We present a pilot empirical study focused on matches and mismatches between hand-annotated linear mention spans and automatically parsed syntactic trees that follow Universal Dependencies conventions. The study covers 9 datasets for 8 different languages.
%R 10.18653/v1/2021.findings-emnlp.303
%U https://aclanthology.org/2021.findings-emnlp.303
%U https://doi.org/10.18653/v1/2021.findings-emnlp.303
%P 3570-3576
Markdown (Informal)
[Do UD Trees Match Mention Spans in Coreference Annotations?](https://aclanthology.org/2021.findings-emnlp.303) (Popel et al., Findings 2021)
ACL
- Martin Popel, Zdeněk Žabokrtský, Anna Nedoluzhko, Michal Novák, and Daniel Zeman. 2021. Do UD Trees Match Mention Spans in Coreference Annotations?. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3570–3576, Punta Cana, Dominican Republic. Association for Computational Linguistics.