@inproceedings{nguyen-etal-2023-span,
title = "Span-based Named Entity Recognition by Generating and Compressing Information",
author = "Nguyen, Nhung T. H. and
Miwa, Makoto and
Ananiadou, Sophia",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.eacl-main.146",
doi = "10.18653/v1/2023.eacl-main.146",
pages = "1984--1996",
abstract = "The information bottleneck (IB) principle has been proven effective in various NLP applications. The existing work, however, only used either generative or information compression models to improve the performance of the target task. In this paper, we propose to combine the two types of IB models into one system to enhance Named Entity Recognition (NER).For one type of IB model, we incorporate two unsupervised generative components, span reconstruction and synonym generation, into a span-based NER system. The span reconstruction ensures that the contextualised span representation keeps the span information, while the synonym generation makes synonyms have similar representations even in different contexts. For the other type of IB model, we add a supervised IB layer that performs information compression into the system to preserve useful features for NER in the resulting span representations. Experiments on five different corpora indicate that jointly training both generative and information compression models can enhance the performance of the baseline span-based NER system. Our source code is publicly available at \url{https://github.com/nguyennth/joint-ib-models}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2023-span">
<titleInfo>
<title>Span-based Named Entity Recognition by Generating and Compressing Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nhung</namePart>
<namePart type="given">T</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The information bottleneck (IB) principle has been proven effective in various NLP applications. The existing work, however, only used either generative or information compression models to improve the performance of the target task. In this paper, we propose to combine the two types of IB models into one system to enhance Named Entity Recognition (NER).For one type of IB model, we incorporate two unsupervised generative components, span reconstruction and synonym generation, into a span-based NER system. The span reconstruction ensures that the contextualised span representation keeps the span information, while the synonym generation makes synonyms have similar representations even in different contexts. For the other type of IB model, we add a supervised IB layer that performs information compression into the system to preserve useful features for NER in the resulting span representations. Experiments on five different corpora indicate that jointly training both generative and information compression models can enhance the performance of the baseline span-based NER system. Our source code is publicly available at https://github.com/nguyennth/joint-ib-models.</abstract>
<identifier type="citekey">nguyen-etal-2023-span</identifier>
<identifier type="doi">10.18653/v1/2023.eacl-main.146</identifier>
<location>
<url>https://aclanthology.org/2023.eacl-main.146</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1984</start>
<end>1996</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Span-based Named Entity Recognition by Generating and Compressing Information
%A Nguyen, Nhung T. H.
%A Miwa, Makoto
%A Ananiadou, Sophia
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F nguyen-etal-2023-span
%X The information bottleneck (IB) principle has been proven effective in various NLP applications. The existing work, however, only used either generative or information compression models to improve the performance of the target task. In this paper, we propose to combine the two types of IB models into one system to enhance Named Entity Recognition (NER).For one type of IB model, we incorporate two unsupervised generative components, span reconstruction and synonym generation, into a span-based NER system. The span reconstruction ensures that the contextualised span representation keeps the span information, while the synonym generation makes synonyms have similar representations even in different contexts. For the other type of IB model, we add a supervised IB layer that performs information compression into the system to preserve useful features for NER in the resulting span representations. Experiments on five different corpora indicate that jointly training both generative and information compression models can enhance the performance of the baseline span-based NER system. Our source code is publicly available at https://github.com/nguyennth/joint-ib-models.
%R 10.18653/v1/2023.eacl-main.146
%U https://aclanthology.org/2023.eacl-main.146
%U https://doi.org/10.18653/v1/2023.eacl-main.146
%P 1984-1996
Markdown (Informal)
[Span-based Named Entity Recognition by Generating and Compressing Information](https://aclanthology.org/2023.eacl-main.146) (Nguyen et al., EACL 2023)
ACL