@inproceedings{seeha-etal-2020-thailmcut,
title = "{T}hai{LMC}ut: Unsupervised Pretraining for {T}hai Word Segmentation",
author = {Seeha, Suteera and
Bilan, Ivan and
Mamani Sanchez, Liliana and
Huber, Johannes and
Matuschek, Michael and
Sch{\"u}tze, Hinrich},
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-1.858",
pages = "6947--6957",
abstract = "We propose ThaiLMCut, a semi-supervised approach for Thai word segmentation which utilizes a bi-directional character language model (LM) as a way to leverage useful linguistic knowledge from unlabeled data. After the language model is trained on substantial unlabeled corpora, the weights of its embedding and recurrent layers are transferred to a supervised word segmentation model which continues fine-tuning them on a word segmentation task. Our experimental results demonstrate that applying the LM always leads to a performance gain, especially when the amount of labeled data is small. In such cases, the F1 Score increased by up to 2.02{\%}. Even on abig labeled dataset, a small improvement gain can still be obtained. The approach has also shown to be very beneficial for out-of-domain settings with a gain in F1 Score of up to 3.13{\%}. Finally, we show that ThaiLMCut can outperform other open source state-of-the-art models achieving an F1 Score of 98.78{\%} on the standard benchmark, InterBEST2009.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seeha-etal-2020-thailmcut">
<titleInfo>
<title>ThaiLMCut: Unsupervised Pretraining for Thai Word Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suteera</namePart>
<namePart type="family">Seeha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Bilan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liliana</namePart>
<namePart type="family">Mamani Sanchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Huber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Matuschek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schütze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">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>We propose ThaiLMCut, a semi-supervised approach for Thai word segmentation which utilizes a bi-directional character language model (LM) as a way to leverage useful linguistic knowledge from unlabeled data. After the language model is trained on substantial unlabeled corpora, the weights of its embedding and recurrent layers are transferred to a supervised word segmentation model which continues fine-tuning them on a word segmentation task. Our experimental results demonstrate that applying the LM always leads to a performance gain, especially when the amount of labeled data is small. In such cases, the F1 Score increased by up to 2.02%. Even on abig labeled dataset, a small improvement gain can still be obtained. The approach has also shown to be very beneficial for out-of-domain settings with a gain in F1 Score of up to 3.13%. Finally, we show that ThaiLMCut can outperform other open source state-of-the-art models achieving an F1 Score of 98.78% on the standard benchmark, InterBEST2009.</abstract>
<identifier type="citekey">seeha-etal-2020-thailmcut</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.858</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6947</start>
<end>6957</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ThaiLMCut: Unsupervised Pretraining for Thai Word Segmentation
%A Seeha, Suteera
%A Bilan, Ivan
%A Mamani Sanchez, Liliana
%A Huber, Johannes
%A Matuschek, Michael
%A Schütze, Hinrich
%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 English
%F seeha-etal-2020-thailmcut
%X We propose ThaiLMCut, a semi-supervised approach for Thai word segmentation which utilizes a bi-directional character language model (LM) as a way to leverage useful linguistic knowledge from unlabeled data. After the language model is trained on substantial unlabeled corpora, the weights of its embedding and recurrent layers are transferred to a supervised word segmentation model which continues fine-tuning them on a word segmentation task. Our experimental results demonstrate that applying the LM always leads to a performance gain, especially when the amount of labeled data is small. In such cases, the F1 Score increased by up to 2.02%. Even on abig labeled dataset, a small improvement gain can still be obtained. The approach has also shown to be very beneficial for out-of-domain settings with a gain in F1 Score of up to 3.13%. Finally, we show that ThaiLMCut can outperform other open source state-of-the-art models achieving an F1 Score of 98.78% on the standard benchmark, InterBEST2009.
%U https://aclanthology.org/2020.lrec-1.858
%P 6947-6957
Markdown (Informal)
[ThaiLMCut: Unsupervised Pretraining for Thai Word Segmentation](https://aclanthology.org/2020.lrec-1.858) (Seeha et al., LREC 2020)
ACL
- Suteera Seeha, Ivan Bilan, Liliana Mamani Sanchez, Johannes Huber, Michael Matuschek, and Hinrich Schütze. 2020. ThaiLMCut: Unsupervised Pretraining for Thai Word Segmentation. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6947–6957, Marseille, France. European Language Resources Association.