@inproceedings{miculicich-henderson-2022-graph,
title = "Graph Refinement for Coreference Resolution",
author = "Miculicich, Lesly and
Henderson, James",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.215/",
doi = "10.18653/v1/2022.findings-acl.215",
pages = "2732--2742",
abstract = "The state-of-the-art models for coreference resolution are based on independent mention pair-wise decisions. We propose a modelling approach that learns coreference at the document-level and takes global decisions. For this purpose, we model coreference links in a graph structure where the nodes are tokens in the text, and the edges represent the relationship between them. Our model predicts the graph in a non-autoregressive manner, then iteratively refines it based on previous predictions, allowing global dependencies between decisions. The experimental results show improvements over various baselines, reinforcing the hypothesis that document-level information improves conference resolution."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miculicich-henderson-2022-graph">
<titleInfo>
<title>Graph Refinement for Coreference Resolution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lesly</namePart>
<namePart type="family">Miculicich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Henderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</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">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The state-of-the-art models for coreference resolution are based on independent mention pair-wise decisions. We propose a modelling approach that learns coreference at the document-level and takes global decisions. For this purpose, we model coreference links in a graph structure where the nodes are tokens in the text, and the edges represent the relationship between them. Our model predicts the graph in a non-autoregressive manner, then iteratively refines it based on previous predictions, allowing global dependencies between decisions. The experimental results show improvements over various baselines, reinforcing the hypothesis that document-level information improves conference resolution.</abstract>
<identifier type="citekey">miculicich-henderson-2022-graph</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.215</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.215/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2732</start>
<end>2742</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Graph Refinement for Coreference Resolution
%A Miculicich, Lesly
%A Henderson, James
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F miculicich-henderson-2022-graph
%X The state-of-the-art models for coreference resolution are based on independent mention pair-wise decisions. We propose a modelling approach that learns coreference at the document-level and takes global decisions. For this purpose, we model coreference links in a graph structure where the nodes are tokens in the text, and the edges represent the relationship between them. Our model predicts the graph in a non-autoregressive manner, then iteratively refines it based on previous predictions, allowing global dependencies between decisions. The experimental results show improvements over various baselines, reinforcing the hypothesis that document-level information improves conference resolution.
%R 10.18653/v1/2022.findings-acl.215
%U https://aclanthology.org/2022.findings-acl.215/
%U https://doi.org/10.18653/v1/2022.findings-acl.215
%P 2732-2742
Markdown (Informal)
[Graph Refinement for Coreference Resolution](https://aclanthology.org/2022.findings-acl.215/) (Miculicich & Henderson, Findings 2022)
ACL
- Lesly Miculicich and James Henderson. 2022. Graph Refinement for Coreference Resolution. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2732–2742, Dublin, Ireland. Association for Computational Linguistics.