@inproceedings{cross-etal-2023-glossy,
title = "Glossy Bytes: Neural Glossing using Subword Encoding",
author = "Cross, Ziggy and
Yun, Michelle and
Apparaju, Ananya and
MacCabe, Jata and
Nicolai, Garrett and
Silfverberg, Miikka",
editor = {Nicolai, Garrett and
Chodroff, Eleanor and
Mailhot, Frederic and
{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
booktitle = "Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigmorphon-1.24",
doi = "10.18653/v1/2023.sigmorphon-1.24",
pages = "222--229",
abstract = "This paper presents several different neural subword modelling based approaches to interlinear glossing for seven under-resourced languages as a part of the 2023 SIGMORPHON shared task on interlinear glossing. We experiment with various augmentation and tokenization strategies for both the open and closed tracks of data. We found that while byte-level models may perform well for greater amounts of data, character based approaches remain competitive in their performance in lower resource settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cross-etal-2023-glossy">
<titleInfo>
<title>Glossy Bytes: Neural Glossing using Subword Encoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziggy</namePart>
<namePart type="family">Cross</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michelle</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ananya</namePart>
<namePart type="family">Apparaju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jata</namePart>
<namePart type="family">MacCabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miikka</namePart>
<namePart type="family">Silfverberg</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>Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleanor</namePart>
<namePart type="family">Chodroff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Mailhot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</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>This paper presents several different neural subword modelling based approaches to interlinear glossing for seven under-resourced languages as a part of the 2023 SIGMORPHON shared task on interlinear glossing. We experiment with various augmentation and tokenization strategies for both the open and closed tracks of data. We found that while byte-level models may perform well for greater amounts of data, character based approaches remain competitive in their performance in lower resource settings.</abstract>
<identifier type="citekey">cross-etal-2023-glossy</identifier>
<identifier type="doi">10.18653/v1/2023.sigmorphon-1.24</identifier>
<location>
<url>https://aclanthology.org/2023.sigmorphon-1.24</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>222</start>
<end>229</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Glossy Bytes: Neural Glossing using Subword Encoding
%A Cross, Ziggy
%A Yun, Michelle
%A Apparaju, Ananya
%A MacCabe, Jata
%A Nicolai, Garrett
%A Silfverberg, Miikka
%Y Nicolai, Garrett
%Y Chodroff, Eleanor
%Y Mailhot, Frederic
%Y Çöltekin, Çağrı
%S Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F cross-etal-2023-glossy
%X This paper presents several different neural subword modelling based approaches to interlinear glossing for seven under-resourced languages as a part of the 2023 SIGMORPHON shared task on interlinear glossing. We experiment with various augmentation and tokenization strategies for both the open and closed tracks of data. We found that while byte-level models may perform well for greater amounts of data, character based approaches remain competitive in their performance in lower resource settings.
%R 10.18653/v1/2023.sigmorphon-1.24
%U https://aclanthology.org/2023.sigmorphon-1.24
%U https://doi.org/10.18653/v1/2023.sigmorphon-1.24
%P 222-229
Markdown (Informal)
[Glossy Bytes: Neural Glossing using Subword Encoding](https://aclanthology.org/2023.sigmorphon-1.24) (Cross et al., SIGMORPHON 2023)
ACL
- Ziggy Cross, Michelle Yun, Ananya Apparaju, Jata MacCabe, Garrett Nicolai, and Miikka Silfverberg. 2023. Glossy Bytes: Neural Glossing using Subword Encoding. In Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 222–229, Toronto, Canada. Association for Computational Linguistics.