@inproceedings{yang-etal-2020-ggp,
title = "{GGP}: Glossary Guided Post-processing for Word Embedding Learning",
author = "Yang, Ruosong and
Cao, Jiannong and
Wen, Zhiyuan",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.581/",
pages = "4726--4730",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "Word embedding learning is the task to map each word into a low-dimensional and continuous vector based on a large corpus. To enhance corpus based word embedding models, researchers utilize domain knowledge to learn more distinguishable representations via joint optimization and post-processing based models. However, joint optimization based models require much training time. Existing post-processing models mostly consider semantic knowledge while learned embedding models show less functional information. Glossary is a comprehensive linguistic resource. And in previous works, the glossary is usually used to enhance the word representations via joint optimization based methods. In this paper, we post-process pre-trained word embedding models with incorporating the glossary and capture more topical and functional information. We propose GGP (Glossary Guided Post-processing word embedding) model which consists of a global post-processing function to fine-tune each word vector, and an auto-encoding model to learn sense representations, furthermore, constrains each post-processed word representation and the composition of its sense representations to be similar. We evaluate our model by comparing it with two state-of-the-art models on six word topical/functional similarity datasets, and the results show that it outperforms competitors by an average of 4.1{\%} across all datasets. And our model outperforms GloVe by more than 7{\%}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2020-ggp">
<titleInfo>
<title>GGP: Glossary Guided Post-processing for Word Embedding Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruosong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiannong</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Word embedding learning is the task to map each word into a low-dimensional and continuous vector based on a large corpus. To enhance corpus based word embedding models, researchers utilize domain knowledge to learn more distinguishable representations via joint optimization and post-processing based models. However, joint optimization based models require much training time. Existing post-processing models mostly consider semantic knowledge while learned embedding models show less functional information. Glossary is a comprehensive linguistic resource. And in previous works, the glossary is usually used to enhance the word representations via joint optimization based methods. In this paper, we post-process pre-trained word embedding models with incorporating the glossary and capture more topical and functional information. We propose GGP (Glossary Guided Post-processing word embedding) model which consists of a global post-processing function to fine-tune each word vector, and an auto-encoding model to learn sense representations, furthermore, constrains each post-processed word representation and the composition of its sense representations to be similar. We evaluate our model by comparing it with two state-of-the-art models on six word topical/functional similarity datasets, and the results show that it outperforms competitors by an average of 4.1% across all datasets. And our model outperforms GloVe by more than 7%.</abstract>
<identifier type="citekey">yang-etal-2020-ggp</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.581/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4726</start>
<end>4730</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GGP: Glossary Guided Post-processing for Word Embedding Learning
%A Yang, Ruosong
%A Cao, Jiannong
%A Wen, Zhiyuan
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F yang-etal-2020-ggp
%X Word embedding learning is the task to map each word into a low-dimensional and continuous vector based on a large corpus. To enhance corpus based word embedding models, researchers utilize domain knowledge to learn more distinguishable representations via joint optimization and post-processing based models. However, joint optimization based models require much training time. Existing post-processing models mostly consider semantic knowledge while learned embedding models show less functional information. Glossary is a comprehensive linguistic resource. And in previous works, the glossary is usually used to enhance the word representations via joint optimization based methods. In this paper, we post-process pre-trained word embedding models with incorporating the glossary and capture more topical and functional information. We propose GGP (Glossary Guided Post-processing word embedding) model which consists of a global post-processing function to fine-tune each word vector, and an auto-encoding model to learn sense representations, furthermore, constrains each post-processed word representation and the composition of its sense representations to be similar. We evaluate our model by comparing it with two state-of-the-art models on six word topical/functional similarity datasets, and the results show that it outperforms competitors by an average of 4.1% across all datasets. And our model outperforms GloVe by more than 7%.
%U https://aclanthology.org/2020.lrec-1.581/
%P 4726-4730
Markdown (Informal)
[GGP: Glossary Guided Post-processing for Word Embedding Learning](https://aclanthology.org/2020.lrec-1.581/) (Yang et al., LREC 2020)
ACL