@inproceedings{levine-2022-sharing,
title = "Sharing Data by Language Family: Data Augmentation for {R}omance Language Morpheme Segmentation",
author = "Levine, Lauren",
editor = "Nicolai, Garrett and
Chodroff, Eleanor",
booktitle = "Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = jul,
year = "2022",
address = "Seattle, Washington",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sigmorphon-1.12",
doi = "10.18653/v1/2022.sigmorphon-1.12",
pages = "117--123",
abstract = "This paper presents a basic character level sequence-to-sequence approach to morpheme segmentation for the following Romance languages: French, Italian, and Spanish. We experiment with adding a small set of additional linguistic features, as well as with sharing training data between sister languages for morphological categories with low performance in single language base models. We find that while the additional linguistic features were generally not helpful in this instance, data augmentation between sister languages did help to raise the scores of some individual morphological categories, but did not consistently result in an overall improvement when considering the aggregate of the categories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="levine-2022-sharing">
<titleInfo>
<title>Sharing Data by Language Family: Data Augmentation for Romance Language Morpheme Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lauren</namePart>
<namePart type="family">Levine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th 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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a basic character level sequence-to-sequence approach to morpheme segmentation for the following Romance languages: French, Italian, and Spanish. We experiment with adding a small set of additional linguistic features, as well as with sharing training data between sister languages for morphological categories with low performance in single language base models. We find that while the additional linguistic features were generally not helpful in this instance, data augmentation between sister languages did help to raise the scores of some individual morphological categories, but did not consistently result in an overall improvement when considering the aggregate of the categories.</abstract>
<identifier type="citekey">levine-2022-sharing</identifier>
<identifier type="doi">10.18653/v1/2022.sigmorphon-1.12</identifier>
<location>
<url>https://aclanthology.org/2022.sigmorphon-1.12</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>117</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sharing Data by Language Family: Data Augmentation for Romance Language Morpheme Segmentation
%A Levine, Lauren
%Y Nicolai, Garrett
%Y Chodroff, Eleanor
%S Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington
%F levine-2022-sharing
%X This paper presents a basic character level sequence-to-sequence approach to morpheme segmentation for the following Romance languages: French, Italian, and Spanish. We experiment with adding a small set of additional linguistic features, as well as with sharing training data between sister languages for morphological categories with low performance in single language base models. We find that while the additional linguistic features were generally not helpful in this instance, data augmentation between sister languages did help to raise the scores of some individual morphological categories, but did not consistently result in an overall improvement when considering the aggregate of the categories.
%R 10.18653/v1/2022.sigmorphon-1.12
%U https://aclanthology.org/2022.sigmorphon-1.12
%U https://doi.org/10.18653/v1/2022.sigmorphon-1.12
%P 117-123
Markdown (Informal)
[Sharing Data by Language Family: Data Augmentation for Romance Language Morpheme Segmentation](https://aclanthology.org/2022.sigmorphon-1.12) (Levine, SIGMORPHON 2022)
ACL