@inproceedings{liu-etal-2021-morphological,
title = "Morphological Segmentation for {S}eneca",
author = "Liu, Zoey and
Jimerson, Robert and
Prud{'}hommeaux, Emily",
editor = "Mager, Manuel and
Oncevay, Arturo and
Rios, Annette and
Ruiz, Ivan Vladimir Meza and
Palmer, Alexis and
Neubig, Graham and
Kann, Katharina",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.americasnlp-1.10",
doi = "10.18653/v1/2021.americasnlp-1.10",
pages = "90--101",
abstract = "This study takes up the task of low-resource morphological segmentation for Seneca, a critically endangered and morphologically complex Native American language primarily spoken in what is now New York State and Ontario. The labeled data in our experiments comes from two sources: one digitized from a publicly available grammar book and the other collected from informal sources. We treat these two sources as distinct domains and investigate different evaluation designs for model selection. The first design abides by standard practices and evaluate models with the in-domain development set, while the second one carries out evaluation using a development domain, or the out-of-domain development set. Across a series of monolingual and crosslinguistic training settings, our results demonstrate the utility of neural encoder-decoder architecture when coupled with multi-task learning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-morphological">
<titleInfo>
<title>Morphological Segmentation for Seneca</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zoey</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Jimerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Prud’hommeaux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Rios</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="given">Meza</namePart>
<namePart type="family">Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This study takes up the task of low-resource morphological segmentation for Seneca, a critically endangered and morphologically complex Native American language primarily spoken in what is now New York State and Ontario. The labeled data in our experiments comes from two sources: one digitized from a publicly available grammar book and the other collected from informal sources. We treat these two sources as distinct domains and investigate different evaluation designs for model selection. The first design abides by standard practices and evaluate models with the in-domain development set, while the second one carries out evaluation using a development domain, or the out-of-domain development set. Across a series of monolingual and crosslinguistic training settings, our results demonstrate the utility of neural encoder-decoder architecture when coupled with multi-task learning.</abstract>
<identifier type="citekey">liu-etal-2021-morphological</identifier>
<identifier type="doi">10.18653/v1/2021.americasnlp-1.10</identifier>
<location>
<url>https://aclanthology.org/2021.americasnlp-1.10</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>90</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphological Segmentation for Seneca
%A Liu, Zoey
%A Jimerson, Robert
%A Prud’hommeaux, Emily
%Y Mager, Manuel
%Y Oncevay, Arturo
%Y Rios, Annette
%Y Ruiz, Ivan Vladimir Meza
%Y Palmer, Alexis
%Y Neubig, Graham
%Y Kann, Katharina
%S Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F liu-etal-2021-morphological
%X This study takes up the task of low-resource morphological segmentation for Seneca, a critically endangered and morphologically complex Native American language primarily spoken in what is now New York State and Ontario. The labeled data in our experiments comes from two sources: one digitized from a publicly available grammar book and the other collected from informal sources. We treat these two sources as distinct domains and investigate different evaluation designs for model selection. The first design abides by standard practices and evaluate models with the in-domain development set, while the second one carries out evaluation using a development domain, or the out-of-domain development set. Across a series of monolingual and crosslinguistic training settings, our results demonstrate the utility of neural encoder-decoder architecture when coupled with multi-task learning.
%R 10.18653/v1/2021.americasnlp-1.10
%U https://aclanthology.org/2021.americasnlp-1.10
%U https://doi.org/10.18653/v1/2021.americasnlp-1.10
%P 90-101
Markdown (Informal)
[Morphological Segmentation for Seneca](https://aclanthology.org/2021.americasnlp-1.10) (Liu et al., AmericasNLP 2021)
ACL
- Zoey Liu, Robert Jimerson, and Emily Prud’hommeaux. 2021. Morphological Segmentation for Seneca. In Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas, pages 90–101, Online. Association for Computational Linguistics.