@inproceedings{ahmed-etal-2023-2,
title = "$2*n$ is better than $n^2$: Decomposing Event Coreference Resolution into Two Tractable Problems",
author = "Ahmed, Shafiuddin Rehan and
Nath, Abhijnan and
Martin, James H. and
Krishnaswamy, Nikhil",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.100",
doi = "10.18653/v1/2023.findings-acl.100",
pages = "1569--1583",
abstract = "Event Coreference Resolution (ECR) is the task of linking mentions of the same event either within or across documents. Most mention pairs are not coreferent, yet many that are coreferent can be identified through simple techniques such as lemma matching of the event triggers or the sentences in which they appear. Existing methods for training coreference systems sample from a largely skewed distribution, making it difficult for the algorithm to learn coreference beyond surface matching. Additionally, these methods are intractable because of the quadratic operations needed. To address these challenges, we break the problem of ECR into two parts: a) a heuristic to efficiently filter out a large number of non-coreferent pairs, and b) a training approach on a balanced set of coreferent and non-coreferent mention pairs. By following this approach, we show that we get comparable results to the state of the art on two popular ECR datasets while significantly reducing compute requirements. We also analyze the mention pairs that are {``}hard{''} to accurately classify as coreferent or non-coreferentcode repo: $\mathtt{github.com/ahmeshaf/lemma\_ce\_coref}$.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmed-etal-2023-2">
<titleInfo>
<title>2*n is better than n²: Decomposing Event Coreference Resolution into Two Tractable Problems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shafiuddin</namePart>
<namePart type="given">Rehan</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhijnan</namePart>
<namePart type="family">Nath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikhil</namePart>
<namePart type="family">Krishnaswamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Event Coreference Resolution (ECR) is the task of linking mentions of the same event either within or across documents. Most mention pairs are not coreferent, yet many that are coreferent can be identified through simple techniques such as lemma matching of the event triggers or the sentences in which they appear. Existing methods for training coreference systems sample from a largely skewed distribution, making it difficult for the algorithm to learn coreference beyond surface matching. Additionally, these methods are intractable because of the quadratic operations needed. To address these challenges, we break the problem of ECR into two parts: a) a heuristic to efficiently filter out a large number of non-coreferent pairs, and b) a training approach on a balanced set of coreferent and non-coreferent mention pairs. By following this approach, we show that we get comparable results to the state of the art on two popular ECR datasets while significantly reducing compute requirements. We also analyze the mention pairs that are “hard” to accurately classify as coreferent or non-coreferentcode repo: \mathttgithub.com/ahmeshaf/lemma_ce_coref.</abstract>
<identifier type="citekey">ahmed-etal-2023-2</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.100</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.100</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1569</start>
<end>1583</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 2*n is better than n²: Decomposing Event Coreference Resolution into Two Tractable Problems
%A Ahmed, Shafiuddin Rehan
%A Nath, Abhijnan
%A Martin, James H.
%A Krishnaswamy, Nikhil
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ahmed-etal-2023-2
%X Event Coreference Resolution (ECR) is the task of linking mentions of the same event either within or across documents. Most mention pairs are not coreferent, yet many that are coreferent can be identified through simple techniques such as lemma matching of the event triggers or the sentences in which they appear. Existing methods for training coreference systems sample from a largely skewed distribution, making it difficult for the algorithm to learn coreference beyond surface matching. Additionally, these methods are intractable because of the quadratic operations needed. To address these challenges, we break the problem of ECR into two parts: a) a heuristic to efficiently filter out a large number of non-coreferent pairs, and b) a training approach on a balanced set of coreferent and non-coreferent mention pairs. By following this approach, we show that we get comparable results to the state of the art on two popular ECR datasets while significantly reducing compute requirements. We also analyze the mention pairs that are “hard” to accurately classify as coreferent or non-coreferentcode repo: \mathttgithub.com/ahmeshaf/lemma_ce_coref.
%R 10.18653/v1/2023.findings-acl.100
%U https://aclanthology.org/2023.findings-acl.100
%U https://doi.org/10.18653/v1/2023.findings-acl.100
%P 1569-1583
Markdown (Informal)
[2*n is better than n2: Decomposing Event Coreference Resolution into Two Tractable Problems](https://aclanthology.org/2023.findings-acl.100) (Ahmed et al., Findings 2023)
ACL