@inproceedings{alsulaimani-moreau-2023-improving,
title = "Improving Diachronic Word Sense Induction with a Nonparametric {B}ayesian method",
author = "Alsulaimani, Ashjan and
Moreau, Erwan",
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.567",
doi = "10.18653/v1/2023.findings-acl.567",
pages = "8908--8925",
abstract = "Diachronic Word Sense Induction (DWSI) is the task of inducing the temporal representations of a word meaning from the context, as a set of senses and their prevalence over time. We introduce two new models for DWSI, based on topic modelling techniques: one is based on Hierarchical Dirichlet Processes (HDP), a nonparametric model; the other is based on the Dynamic Embedded Topic Model (DETM), a recent dynamic neural model. We evaluate these models against two state of the art DWSI models, using a time-stamped labelled dataset from the biomedical domain. We demonstrate that the two proposed models perform better than the state of the art. In particular, the HDP-based model drastically outperforms all the other models, including the dynamic neural model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alsulaimani-moreau-2023-improving">
<titleInfo>
<title>Improving Diachronic Word Sense Induction with a Nonparametric Bayesian method</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashjan</namePart>
<namePart type="family">Alsulaimani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erwan</namePart>
<namePart type="family">Moreau</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>Diachronic Word Sense Induction (DWSI) is the task of inducing the temporal representations of a word meaning from the context, as a set of senses and their prevalence over time. We introduce two new models for DWSI, based on topic modelling techniques: one is based on Hierarchical Dirichlet Processes (HDP), a nonparametric model; the other is based on the Dynamic Embedded Topic Model (DETM), a recent dynamic neural model. We evaluate these models against two state of the art DWSI models, using a time-stamped labelled dataset from the biomedical domain. We demonstrate that the two proposed models perform better than the state of the art. In particular, the HDP-based model drastically outperforms all the other models, including the dynamic neural model.</abstract>
<identifier type="citekey">alsulaimani-moreau-2023-improving</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.567</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.567</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>8908</start>
<end>8925</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Diachronic Word Sense Induction with a Nonparametric Bayesian method
%A Alsulaimani, Ashjan
%A Moreau, Erwan
%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 alsulaimani-moreau-2023-improving
%X Diachronic Word Sense Induction (DWSI) is the task of inducing the temporal representations of a word meaning from the context, as a set of senses and their prevalence over time. We introduce two new models for DWSI, based on topic modelling techniques: one is based on Hierarchical Dirichlet Processes (HDP), a nonparametric model; the other is based on the Dynamic Embedded Topic Model (DETM), a recent dynamic neural model. We evaluate these models against two state of the art DWSI models, using a time-stamped labelled dataset from the biomedical domain. We demonstrate that the two proposed models perform better than the state of the art. In particular, the HDP-based model drastically outperforms all the other models, including the dynamic neural model.
%R 10.18653/v1/2023.findings-acl.567
%U https://aclanthology.org/2023.findings-acl.567
%U https://doi.org/10.18653/v1/2023.findings-acl.567
%P 8908-8925
Markdown (Informal)
[Improving Diachronic Word Sense Induction with a Nonparametric Bayesian method](https://aclanthology.org/2023.findings-acl.567) (Alsulaimani & Moreau, Findings 2023)
ACL