@inproceedings{barba-etal-2022-extend,
title = "{E}xt{E}n{D}: Extractive Entity Disambiguation",
author = "Barba, Edoardo and
Procopio, Luigi and
Navigli, Roberto",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.177",
doi = "10.18653/v1/2022.acl-long.177",
pages = "2478--2488",
abstract = "Local models for Entity Disambiguation (ED) have today become extremely powerful, in most part thanks to the advent of large pre-trained language models. However, despite their significant performance achievements, most of these approaches frame ED through classification formulations that have intrinsic limitations, both computationally and from a modeling perspective. In contrast with this trend, here we propose ExtEnD, a novel local formulation for ED where we frame this task as a text extraction problem, and present two Transformer-based architectures that implement it. Based on experiments in and out of domain, and training over two different data regimes, we find our approach surpasses all its competitors in terms of both data efficiency and raw performance. ExtEnD outperforms its alternatives by as few as 6 F1 points on the more constrained of the two data regimes and, when moving to the other higher-resourced regime, sets a new state of the art on 4 out of 4 benchmarks under consideration, with average improvements of 0.7 F1 points overall and 1.1 F1 points out of domain. In addition, to gain better insights from our results, we also perform a fine-grained evaluation of our performances on different classes of label frequency, along with an ablation study of our architectural choices and an error analysis. We release our code and models for research purposes at \url{https://github.com/SapienzaNLP/extend}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="barba-etal-2022-extend">
<titleInfo>
<title>ExtEnD: Extractive Entity Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="family">Barba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luigi</namePart>
<namePart type="family">Procopio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>Local models for Entity Disambiguation (ED) have today become extremely powerful, in most part thanks to the advent of large pre-trained language models. However, despite their significant performance achievements, most of these approaches frame ED through classification formulations that have intrinsic limitations, both computationally and from a modeling perspective. In contrast with this trend, here we propose ExtEnD, a novel local formulation for ED where we frame this task as a text extraction problem, and present two Transformer-based architectures that implement it. Based on experiments in and out of domain, and training over two different data regimes, we find our approach surpasses all its competitors in terms of both data efficiency and raw performance. ExtEnD outperforms its alternatives by as few as 6 F1 points on the more constrained of the two data regimes and, when moving to the other higher-resourced regime, sets a new state of the art on 4 out of 4 benchmarks under consideration, with average improvements of 0.7 F1 points overall and 1.1 F1 points out of domain. In addition, to gain better insights from our results, we also perform a fine-grained evaluation of our performances on different classes of label frequency, along with an ablation study of our architectural choices and an error analysis. We release our code and models for research purposes at https://github.com/SapienzaNLP/extend.</abstract>
<identifier type="citekey">barba-etal-2022-extend</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.177</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.177</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2478</start>
<end>2488</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ExtEnD: Extractive Entity Disambiguation
%A Barba, Edoardo
%A Procopio, Luigi
%A Navigli, Roberto
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F barba-etal-2022-extend
%X Local models for Entity Disambiguation (ED) have today become extremely powerful, in most part thanks to the advent of large pre-trained language models. However, despite their significant performance achievements, most of these approaches frame ED through classification formulations that have intrinsic limitations, both computationally and from a modeling perspective. In contrast with this trend, here we propose ExtEnD, a novel local formulation for ED where we frame this task as a text extraction problem, and present two Transformer-based architectures that implement it. Based on experiments in and out of domain, and training over two different data regimes, we find our approach surpasses all its competitors in terms of both data efficiency and raw performance. ExtEnD outperforms its alternatives by as few as 6 F1 points on the more constrained of the two data regimes and, when moving to the other higher-resourced regime, sets a new state of the art on 4 out of 4 benchmarks under consideration, with average improvements of 0.7 F1 points overall and 1.1 F1 points out of domain. In addition, to gain better insights from our results, we also perform a fine-grained evaluation of our performances on different classes of label frequency, along with an ablation study of our architectural choices and an error analysis. We release our code and models for research purposes at https://github.com/SapienzaNLP/extend.
%R 10.18653/v1/2022.acl-long.177
%U https://aclanthology.org/2022.acl-long.177
%U https://doi.org/10.18653/v1/2022.acl-long.177
%P 2478-2488
Markdown (Informal)
[ExtEnD: Extractive Entity Disambiguation](https://aclanthology.org/2022.acl-long.177) (Barba et al., ACL 2022)
ACL
- Edoardo Barba, Luigi Procopio, and Roberto Navigli. 2022. ExtEnD: Extractive Entity Disambiguation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2478–2488, Dublin, Ireland. Association for Computational Linguistics.