@inproceedings{chormai-etal-2020-syllable,
title = "Syllable-based Neural {T}hai Word Segmentation",
author = "Chormai, Pattarawat and
Prasertsom, Ponrawee and
Cheevaprawatdomrong, Jin and
Rutherford, Attapol",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.407/",
doi = "10.18653/v1/2020.coling-main.407",
pages = "4619--4637",
abstract = "Word segmentation is a challenging pre-processing step for Thai Natural Language Processing due to the lack of explicit word boundaries. The previous systems rely on powerful neural network architecture alone and ignore linguistic substructures of Thai words. We utilize the linguistic observation that Thai strings can be segmented into syllables, which should narrow down the search space for the word boundaries and provide helpful features. Here, we propose a neural Thai Word Segmenter that uses syllable embeddings to capture linguistic constraints and uses dilated CNN filters to capture the environment of each character. Within this goal, we develop the first ML-based Thai orthographical syllable segmenter, which yields syllable embeddings to be used as features by the word segmenter. Our word segmentation system outperforms the previous state-of-the-art system in both speed and accuracy on both in-domain and out-domain datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chormai-etal-2020-syllable">
<titleInfo>
<title>Syllable-based Neural Thai Word Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pattarawat</namePart>
<namePart type="family">Chormai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ponrawee</namePart>
<namePart type="family">Prasertsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Cheevaprawatdomrong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Attapol</namePart>
<namePart type="family">Rutherford</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word segmentation is a challenging pre-processing step for Thai Natural Language Processing due to the lack of explicit word boundaries. The previous systems rely on powerful neural network architecture alone and ignore linguistic substructures of Thai words. We utilize the linguistic observation that Thai strings can be segmented into syllables, which should narrow down the search space for the word boundaries and provide helpful features. Here, we propose a neural Thai Word Segmenter that uses syllable embeddings to capture linguistic constraints and uses dilated CNN filters to capture the environment of each character. Within this goal, we develop the first ML-based Thai orthographical syllable segmenter, which yields syllable embeddings to be used as features by the word segmenter. Our word segmentation system outperforms the previous state-of-the-art system in both speed and accuracy on both in-domain and out-domain datasets.</abstract>
<identifier type="citekey">chormai-etal-2020-syllable</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.407</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.407/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>4619</start>
<end>4637</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Syllable-based Neural Thai Word Segmentation
%A Chormai, Pattarawat
%A Prasertsom, Ponrawee
%A Cheevaprawatdomrong, Jin
%A Rutherford, Attapol
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F chormai-etal-2020-syllable
%X Word segmentation is a challenging pre-processing step for Thai Natural Language Processing due to the lack of explicit word boundaries. The previous systems rely on powerful neural network architecture alone and ignore linguistic substructures of Thai words. We utilize the linguistic observation that Thai strings can be segmented into syllables, which should narrow down the search space for the word boundaries and provide helpful features. Here, we propose a neural Thai Word Segmenter that uses syllable embeddings to capture linguistic constraints and uses dilated CNN filters to capture the environment of each character. Within this goal, we develop the first ML-based Thai orthographical syllable segmenter, which yields syllable embeddings to be used as features by the word segmenter. Our word segmentation system outperforms the previous state-of-the-art system in both speed and accuracy on both in-domain and out-domain datasets.
%R 10.18653/v1/2020.coling-main.407
%U https://aclanthology.org/2020.coling-main.407/
%U https://doi.org/10.18653/v1/2020.coling-main.407
%P 4619-4637
Markdown (Informal)
[Syllable-based Neural Thai Word Segmentation](https://aclanthology.org/2020.coling-main.407/) (Chormai et al., COLING 2020)
ACL
- Pattarawat Chormai, Ponrawee Prasertsom, Jin Cheevaprawatdomrong, and Attapol Rutherford. 2020. Syllable-based Neural Thai Word Segmentation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4619–4637, Barcelona, Spain (Online). International Committee on Computational Linguistics.