@inproceedings{ginn-palmer-2023-robust,
title = "Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context",
author = "Ginn, Michael and
Palmer, Alexis",
editor = "Hupkes, Dieuwke and
Dankers, Verna and
Batsuren, Khuyagbaatar and
Sinha, Koustuv and
Kazemnejad, Amirhossein and
Christodoulopoulos, Christos and
Cotterell, Ryan and
Bruni, Elia",
booktitle = "Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.genbench-1.7",
doi = "10.18653/v1/2023.genbench-1.7",
pages = "89--98",
abstract = "Generalization is of particular importance in resource-constrained settings, where the available training data may represent only a small fraction of the distribution of possible texts. We investigate the ability of morpheme labeling models to generalize by evaluating their performance on unseen genres of text, and we experiment with strategies for closing the gap between performance on in-distribution and out-of-distribution data. Specifically, we use weight decay optimization, output denoising, and iterative pseudo-labeling, and achieve a 2{\%} improvement on a test set containing texts from unseen genres. All experiments are performed using texts written in the Mayan language Uspanteko.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ginn-palmer-2023-robust">
<titleInfo>
<title>Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Ginn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verna</namePart>
<namePart type="family">Dankers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khuyagbaatar</namePart>
<namePart type="family">Batsuren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustuv</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amirhossein</namePart>
<namePart type="family">Kazemnejad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elia</namePart>
<namePart type="family">Bruni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generalization is of particular importance in resource-constrained settings, where the available training data may represent only a small fraction of the distribution of possible texts. We investigate the ability of morpheme labeling models to generalize by evaluating their performance on unseen genres of text, and we experiment with strategies for closing the gap between performance on in-distribution and out-of-distribution data. Specifically, we use weight decay optimization, output denoising, and iterative pseudo-labeling, and achieve a 2% improvement on a test set containing texts from unseen genres. All experiments are performed using texts written in the Mayan language Uspanteko.</abstract>
<identifier type="citekey">ginn-palmer-2023-robust</identifier>
<identifier type="doi">10.18653/v1/2023.genbench-1.7</identifier>
<location>
<url>https://aclanthology.org/2023.genbench-1.7</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>89</start>
<end>98</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context
%A Ginn, Michael
%A Palmer, Alexis
%Y Hupkes, Dieuwke
%Y Dankers, Verna
%Y Batsuren, Khuyagbaatar
%Y Sinha, Koustuv
%Y Kazemnejad, Amirhossein
%Y Christodoulopoulos, Christos
%Y Cotterell, Ryan
%Y Bruni, Elia
%S Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F ginn-palmer-2023-robust
%X Generalization is of particular importance in resource-constrained settings, where the available training data may represent only a small fraction of the distribution of possible texts. We investigate the ability of morpheme labeling models to generalize by evaluating their performance on unseen genres of text, and we experiment with strategies for closing the gap between performance on in-distribution and out-of-distribution data. Specifically, we use weight decay optimization, output denoising, and iterative pseudo-labeling, and achieve a 2% improvement on a test set containing texts from unseen genres. All experiments are performed using texts written in the Mayan language Uspanteko.
%R 10.18653/v1/2023.genbench-1.7
%U https://aclanthology.org/2023.genbench-1.7
%U https://doi.org/10.18653/v1/2023.genbench-1.7
%P 89-98
Markdown (Informal)
[Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context](https://aclanthology.org/2023.genbench-1.7) (Ginn & Palmer, GenBench-WS 2023)
ACL