@inproceedings{amrhein-sennrich-2021-suitable-subword,
title = "How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?",
author = "Amrhein, Chantal and
Sennrich, Rico",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.60",
doi = "10.18653/v1/2021.findings-emnlp.60",
pages = "689--705",
abstract = "Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite to evaluate segmentation strategies on different types of morphological phenomena in a controlled, semi-synthetic setting. In our experiments, we compare how well machine translation models trained on subword- and character-level can translate these morphological phenomena. We find that learning to analyse and generate morphologically complex surface representations is still challenging, especially for non-concatenative morphological phenomena like reduplication or vowel harmony and for rare word stems. Based on our results, we recommend that novel text representation strategies be tested on a range of typologically diverse languages to minimise the risk of adopting a strategy that inadvertently disadvantages certain languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="amrhein-sennrich-2021-suitable-subword">
<titleInfo>
<title>How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chantal</namePart>
<namePart type="family">Amrhein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite to evaluate segmentation strategies on different types of morphological phenomena in a controlled, semi-synthetic setting. In our experiments, we compare how well machine translation models trained on subword- and character-level can translate these morphological phenomena. We find that learning to analyse and generate morphologically complex surface representations is still challenging, especially for non-concatenative morphological phenomena like reduplication or vowel harmony and for rare word stems. Based on our results, we recommend that novel text representation strategies be tested on a range of typologically diverse languages to minimise the risk of adopting a strategy that inadvertently disadvantages certain languages.</abstract>
<identifier type="citekey">amrhein-sennrich-2021-suitable-subword</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.60</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.60</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>689</start>
<end>705</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?
%A Amrhein, Chantal
%A Sennrich, Rico
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F amrhein-sennrich-2021-suitable-subword
%X Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite to evaluate segmentation strategies on different types of morphological phenomena in a controlled, semi-synthetic setting. In our experiments, we compare how well machine translation models trained on subword- and character-level can translate these morphological phenomena. We find that learning to analyse and generate morphologically complex surface representations is still challenging, especially for non-concatenative morphological phenomena like reduplication or vowel harmony and for rare word stems. Based on our results, we recommend that novel text representation strategies be tested on a range of typologically diverse languages to minimise the risk of adopting a strategy that inadvertently disadvantages certain languages.
%R 10.18653/v1/2021.findings-emnlp.60
%U https://aclanthology.org/2021.findings-emnlp.60
%U https://doi.org/10.18653/v1/2021.findings-emnlp.60
%P 689-705
Markdown (Informal)
[How Suitable Are Subword Segmentation Strategies for Translating Non-Concatenative Morphology?](https://aclanthology.org/2021.findings-emnlp.60) (Amrhein & Sennrich, Findings 2021)
ACL