@inproceedings{wu-etal-2024-kpeval,
title = "{KPE}val: Towards Fine-Grained Semantic-Based Keyphrase Evaluation",
author = "Wu, Di and
Yin, Da and
Chang, Kai-Wei",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.117",
pages = "1959--1981",
abstract = "Despite the significant advancements in keyphrase extraction and keyphrase generation methods, the predominant approach for evaluation mainly relies on exact matching with human references. This scheme fails to recognize systems that generate keyphrases semantically equivalent to the references or diverse keyphrases that carry practical utility. To better assess the capability of keyphrase systems, we propose KPEval, a comprehensive evaluation framework consisting of four critical aspects: reference agreement, faithfulness, diversity, and utility. For each aspect, we design semantic-based metrics to reflect the evaluation objectives. Meta-evaluation studies demonstrate that our evaluation strategy correlates better with human preferences compared to a range of previously proposed metrics. Using KPEval, we re-evaluate 23 keyphrase systems and discover that (1) established model comparison results have blind-spots especially when considering reference-free evaluation; (2) large language models are underestimated by prior evaluation works; and (3) there is no single best model that can excel in all the aspects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2024-kpeval">
<titleInfo>
<title>KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Da</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the significant advancements in keyphrase extraction and keyphrase generation methods, the predominant approach for evaluation mainly relies on exact matching with human references. This scheme fails to recognize systems that generate keyphrases semantically equivalent to the references or diverse keyphrases that carry practical utility. To better assess the capability of keyphrase systems, we propose KPEval, a comprehensive evaluation framework consisting of four critical aspects: reference agreement, faithfulness, diversity, and utility. For each aspect, we design semantic-based metrics to reflect the evaluation objectives. Meta-evaluation studies demonstrate that our evaluation strategy correlates better with human preferences compared to a range of previously proposed metrics. Using KPEval, we re-evaluate 23 keyphrase systems and discover that (1) established model comparison results have blind-spots especially when considering reference-free evaluation; (2) large language models are underestimated by prior evaluation works; and (3) there is no single best model that can excel in all the aspects.</abstract>
<identifier type="citekey">wu-etal-2024-kpeval</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.117</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>1959</start>
<end>1981</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation
%A Wu, Di
%A Yin, Da
%A Chang, Kai-Wei
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F wu-etal-2024-kpeval
%X Despite the significant advancements in keyphrase extraction and keyphrase generation methods, the predominant approach for evaluation mainly relies on exact matching with human references. This scheme fails to recognize systems that generate keyphrases semantically equivalent to the references or diverse keyphrases that carry practical utility. To better assess the capability of keyphrase systems, we propose KPEval, a comprehensive evaluation framework consisting of four critical aspects: reference agreement, faithfulness, diversity, and utility. For each aspect, we design semantic-based metrics to reflect the evaluation objectives. Meta-evaluation studies demonstrate that our evaluation strategy correlates better with human preferences compared to a range of previously proposed metrics. Using KPEval, we re-evaluate 23 keyphrase systems and discover that (1) established model comparison results have blind-spots especially when considering reference-free evaluation; (2) large language models are underestimated by prior evaluation works; and (3) there is no single best model that can excel in all the aspects.
%U https://aclanthology.org/2024.findings-acl.117
%P 1959-1981
Markdown (Informal)
[KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation](https://aclanthology.org/2024.findings-acl.117) (Wu et al., Findings 2024)
ACL