@inproceedings{pugh-etal-2024-wav2pos,
title = "Wav2pos: Exploring syntactic analysis from audio for {H}ighland {P}uebla {N}ahuatl",
author = "Pugh, Robert and
Sreedhar, Varun and
Tyers, Francis",
editor = "Mager, Manuel and
Ebrahimi, Abteen and
Rijhwani, Shruti and
Oncevay, Arturo and
Chiruzzo, Luis and
Pugh, Robert and
von der Wense, Katharina",
booktitle = "Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.americasnlp-1.13/",
doi = "10.18653/v1/2024.americasnlp-1.13",
pages = "121--126",
abstract = "We describe an approach to part-of-speech tagging from audio with very little human-annotated data, for Highland Puebla Nahuatl, a low-resource language of Mexico. While automatic morphosyntactic analysis is typically trained on annotated textual data, large amounts of text is rarely available for low-resource, marginalized, and/or minority languages, and morphosyntactically-annotated data is even harder to come by. Much of the data from these languages may exist in the form of recordings, often only partially-transcribed or analyzed by field linguists working on language documentation projects. Given this relatively low-availability of text in the low-resource language scenario, we explore end-to-end automated morphosyntactic analysis directly from audio. The experiments described in this paper focus on one piece of morphosyntax, part-of-speech tagging, and builds on existing work in a high-resource setting. We use weak supervision to increase training volume, and explore a few techniques for generating word-level predictions from the acoustic features. Our experiments show promising results, despite less than 400 sentences of audio-aligned, manually-labeled text."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pugh-etal-2024-wav2pos">
<titleInfo>
<title>Wav2pos: Exploring syntactic analysis from audio for Highland Puebla Nahuatl</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Sreedhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)</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">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</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">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">von der Wense</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe an approach to part-of-speech tagging from audio with very little human-annotated data, for Highland Puebla Nahuatl, a low-resource language of Mexico. While automatic morphosyntactic analysis is typically trained on annotated textual data, large amounts of text is rarely available for low-resource, marginalized, and/or minority languages, and morphosyntactically-annotated data is even harder to come by. Much of the data from these languages may exist in the form of recordings, often only partially-transcribed or analyzed by field linguists working on language documentation projects. Given this relatively low-availability of text in the low-resource language scenario, we explore end-to-end automated morphosyntactic analysis directly from audio. The experiments described in this paper focus on one piece of morphosyntax, part-of-speech tagging, and builds on existing work in a high-resource setting. We use weak supervision to increase training volume, and explore a few techniques for generating word-level predictions from the acoustic features. Our experiments show promising results, despite less than 400 sentences of audio-aligned, manually-labeled text.</abstract>
<identifier type="citekey">pugh-etal-2024-wav2pos</identifier>
<identifier type="doi">10.18653/v1/2024.americasnlp-1.13</identifier>
<location>
<url>https://aclanthology.org/2024.americasnlp-1.13/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>121</start>
<end>126</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wav2pos: Exploring syntactic analysis from audio for Highland Puebla Nahuatl
%A Pugh, Robert
%A Sreedhar, Varun
%A Tyers, Francis
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Rijhwani, Shruti
%Y Oncevay, Arturo
%Y Chiruzzo, Luis
%Y Pugh, Robert
%Y von der Wense, Katharina
%S Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F pugh-etal-2024-wav2pos
%X We describe an approach to part-of-speech tagging from audio with very little human-annotated data, for Highland Puebla Nahuatl, a low-resource language of Mexico. While automatic morphosyntactic analysis is typically trained on annotated textual data, large amounts of text is rarely available for low-resource, marginalized, and/or minority languages, and morphosyntactically-annotated data is even harder to come by. Much of the data from these languages may exist in the form of recordings, often only partially-transcribed or analyzed by field linguists working on language documentation projects. Given this relatively low-availability of text in the low-resource language scenario, we explore end-to-end automated morphosyntactic analysis directly from audio. The experiments described in this paper focus on one piece of morphosyntax, part-of-speech tagging, and builds on existing work in a high-resource setting. We use weak supervision to increase training volume, and explore a few techniques for generating word-level predictions from the acoustic features. Our experiments show promising results, despite less than 400 sentences of audio-aligned, manually-labeled text.
%R 10.18653/v1/2024.americasnlp-1.13
%U https://aclanthology.org/2024.americasnlp-1.13/
%U https://doi.org/10.18653/v1/2024.americasnlp-1.13
%P 121-126
Markdown (Informal)
[Wav2pos: Exploring syntactic analysis from audio for Highland Puebla Nahuatl](https://aclanthology.org/2024.americasnlp-1.13/) (Pugh et al., AmericasNLP 2024)
ACL