@inproceedings{brown-2024-improved,
title = "Improved Neural Word Segmentation for Standard {T}ibetan",
author = "Brown, Collin J.",
editor = "Ojha, Atul Kr. and
Ahmadi, Sina and
Cinkov{\'a}, Silvie and
Fransen, Theodorus and
Liu, Chao-Hong and
McCrae, John P.",
booktitle = "Proceedings of the 2nd Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia (EURALI) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.eurali-1.2",
pages = "12--17",
abstract = "As Tibetan is traditionally not written with word delimiters, various means of word segmentation are necessary to prepare data for downstream tasks. Neural word segmentation has proven a successful means of parsing Tibetan text, but current performance lags behind that of neural word segmenters in other languages, such as Chinese or Japanese, and even behind languages with relatively similar orthographic structures, such as Vietnamese or Thai. We apply methods that have proven useful for these latter two languages , in addition to Classical Tibetan, toward the development of a neural word segmenter with the goal of raising the peak performance of Tibetan neural word segmentation to a level comparable to that reached for orthographically similar languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brown-2024-improved">
<titleInfo>
<title>Improved Neural Word Segmentation for Standard Tibetan</title>
</titleInfo>
<name type="personal">
<namePart type="given">Collin</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Brown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia (EURALI) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Ahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvie</namePart>
<namePart type="family">Cinková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Theodorus</namePart>
<namePart type="family">Fransen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As Tibetan is traditionally not written with word delimiters, various means of word segmentation are necessary to prepare data for downstream tasks. Neural word segmentation has proven a successful means of parsing Tibetan text, but current performance lags behind that of neural word segmenters in other languages, such as Chinese or Japanese, and even behind languages with relatively similar orthographic structures, such as Vietnamese or Thai. We apply methods that have proven useful for these latter two languages , in addition to Classical Tibetan, toward the development of a neural word segmenter with the goal of raising the peak performance of Tibetan neural word segmentation to a level comparable to that reached for orthographically similar languages.</abstract>
<identifier type="citekey">brown-2024-improved</identifier>
<location>
<url>https://aclanthology.org/2024.eurali-1.2</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improved Neural Word Segmentation for Standard Tibetan
%A Brown, Collin J.
%Y Ojha, Atul Kr.
%Y Ahmadi, Sina
%Y Cinková, Silvie
%Y Fransen, Theodorus
%Y Liu, Chao-Hong
%Y McCrae, John P.
%S Proceedings of the 2nd Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia (EURALI) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F brown-2024-improved
%X As Tibetan is traditionally not written with word delimiters, various means of word segmentation are necessary to prepare data for downstream tasks. Neural word segmentation has proven a successful means of parsing Tibetan text, but current performance lags behind that of neural word segmenters in other languages, such as Chinese or Japanese, and even behind languages with relatively similar orthographic structures, such as Vietnamese or Thai. We apply methods that have proven useful for these latter two languages , in addition to Classical Tibetan, toward the development of a neural word segmenter with the goal of raising the peak performance of Tibetan neural word segmentation to a level comparable to that reached for orthographically similar languages.
%U https://aclanthology.org/2024.eurali-1.2
%P 12-17
Markdown (Informal)
[Improved Neural Word Segmentation for Standard Tibetan](https://aclanthology.org/2024.eurali-1.2) (Brown, EURALI-WS 2024)
ACL
- Collin J. Brown. 2024. Improved Neural Word Segmentation for Standard Tibetan. In Proceedings of the 2nd Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia (EURALI) @ LREC-COLING 2024, pages 12–17, Torino, Italia. ELRA and ICCL.