@inproceedings{rice-etal-2024-tams,
title = "{TAMS}: Translation-Assisted Morphological Segmentation",
author = "Rice, Enora and
Marashian, Ali and
Gessler, Luke and
Palmer, Alexis and
von der Wense, Katharina",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.366",
pages = "6752--6765",
abstract = "Canonical morphological segmentation is the process of analyzing words into the standard (\textit{aka} underlying) forms of their constituent morphemes.This is a core task in endangered language documentation, and NLP systems have the potential to dramatically speed up this process. In typical language documentation settings, training data for canonical morpheme segmentation is scarce, making it difficult to train high quality models. However, translation data is often much more abundant, and, in this work, we present a method that attempts to leverage translation data in the canonical segmentation task. We propose a character-level sequence-to-sequence model that incorporates representations of translations obtained from pretrained high-resource monolingual language models as an additional signal. Our model outperforms the baseline in a super-low resource setting but yields mixed results on training splits with more data. Additionally, we find that we can achieve strong performance even without needing difficult-to-obtain word level alignments. While further work is needed to make translations useful in higher-resource settings, our model shows promise in severely resource-constrained settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rice-etal-2024-tams">
<titleInfo>
<title>TAMS: Translation-Assisted Morphological Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Enora</namePart>
<namePart type="family">Rice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Marashian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Gessler</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>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">von der Wense</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Canonical morphological segmentation is the process of analyzing words into the standard (aka underlying) forms of their constituent morphemes.This is a core task in endangered language documentation, and NLP systems have the potential to dramatically speed up this process. In typical language documentation settings, training data for canonical morpheme segmentation is scarce, making it difficult to train high quality models. However, translation data is often much more abundant, and, in this work, we present a method that attempts to leverage translation data in the canonical segmentation task. We propose a character-level sequence-to-sequence model that incorporates representations of translations obtained from pretrained high-resource monolingual language models as an additional signal. Our model outperforms the baseline in a super-low resource setting but yields mixed results on training splits with more data. Additionally, we find that we can achieve strong performance even without needing difficult-to-obtain word level alignments. While further work is needed to make translations useful in higher-resource settings, our model shows promise in severely resource-constrained settings.</abstract>
<identifier type="citekey">rice-etal-2024-tams</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.366</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>6752</start>
<end>6765</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TAMS: Translation-Assisted Morphological Segmentation
%A Rice, Enora
%A Marashian, Ali
%A Gessler, Luke
%A Palmer, Alexis
%A von der Wense, Katharina
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F rice-etal-2024-tams
%X Canonical morphological segmentation is the process of analyzing words into the standard (aka underlying) forms of their constituent morphemes.This is a core task in endangered language documentation, and NLP systems have the potential to dramatically speed up this process. In typical language documentation settings, training data for canonical morpheme segmentation is scarce, making it difficult to train high quality models. However, translation data is often much more abundant, and, in this work, we present a method that attempts to leverage translation data in the canonical segmentation task. We propose a character-level sequence-to-sequence model that incorporates representations of translations obtained from pretrained high-resource monolingual language models as an additional signal. Our model outperforms the baseline in a super-low resource setting but yields mixed results on training splits with more data. Additionally, we find that we can achieve strong performance even without needing difficult-to-obtain word level alignments. While further work is needed to make translations useful in higher-resource settings, our model shows promise in severely resource-constrained settings.
%U https://aclanthology.org/2024.acl-long.366
%P 6752-6765
Markdown (Informal)
[TAMS: Translation-Assisted Morphological Segmentation](https://aclanthology.org/2024.acl-long.366) (Rice et al., ACL 2024)
ACL
- Enora Rice, Ali Marashian, Luke Gessler, Alexis Palmer, and Katharina von der Wense. 2024. TAMS: Translation-Assisted Morphological Segmentation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6752–6765, Bangkok, Thailand. Association for Computational Linguistics.