@article{toporkov-agerri-2024-role,
title = "On the Role of Morphological Information for Contextual Lemmatization",
author = "Toporkov, Olia and
Agerri, Rodrigo",
journal = "Computational Linguistics",
volume = "50",
number = "1",
month = mar,
year = "2024",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/2024.cl-1.6",
doi = "10.1162/coli_a_00497",
pages = "157--191",
abstract = "Lemmatization is a natural language processing (NLP) task that consists of producing, from a given inflected word, its canonical form or lemma. Lemmatization is one of the basic tasks that facilitate downstream NLP applications, and is of particular importance for high-inflected languages. Given that the process to obtain a lemma from an inflected word can be explained by looking at its morphosyntactic category, including fine-grained morphosyntactic information to train contextual lemmatizers has become common practice, without considering whether that is the optimum in terms of downstream performance. In order to address this issue, in this article we empirically investigate the role of morphological information to develop contextual lemmatizers in six languages within a varied spectrum of morphological complexity: Basque, Turkish, Russian, Czech, Spanish, and English. Furthermore, and unlike the vast majority of previous work, we also evaluate lemmatizers in out-of-domain settings, which constitutes, after all, their most common application use. The results of our study are rather surprising. It turns out that providing lemmatizers with fine-grained morphological features during training is not that beneficial, not even for agglutinative languages. In fact, modern contextual word representations seem to implicitly encode enough morphological information to obtain competitive contextual lemmatizers without seeing any explicit morphological signal. Moreover, our experiments suggest that the best lemmatizers out-of-domain are those using simple UPOS tags or those trained without morphology and, lastly, that current evaluation practices for lemmatization are not adequate to clearly discriminate between models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toporkov-agerri-2024-role">
<titleInfo>
<title>On the Role of Morphological Information for Contextual Lemmatization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olia</namePart>
<namePart type="family">Toporkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rodrigo</namePart>
<namePart type="family">Agerri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>Lemmatization is a natural language processing (NLP) task that consists of producing, from a given inflected word, its canonical form or lemma. Lemmatization is one of the basic tasks that facilitate downstream NLP applications, and is of particular importance for high-inflected languages. Given that the process to obtain a lemma from an inflected word can be explained by looking at its morphosyntactic category, including fine-grained morphosyntactic information to train contextual lemmatizers has become common practice, without considering whether that is the optimum in terms of downstream performance. In order to address this issue, in this article we empirically investigate the role of morphological information to develop contextual lemmatizers in six languages within a varied spectrum of morphological complexity: Basque, Turkish, Russian, Czech, Spanish, and English. Furthermore, and unlike the vast majority of previous work, we also evaluate lemmatizers in out-of-domain settings, which constitutes, after all, their most common application use. The results of our study are rather surprising. It turns out that providing lemmatizers with fine-grained morphological features during training is not that beneficial, not even for agglutinative languages. In fact, modern contextual word representations seem to implicitly encode enough morphological information to obtain competitive contextual lemmatizers without seeing any explicit morphological signal. Moreover, our experiments suggest that the best lemmatizers out-of-domain are those using simple UPOS tags or those trained without morphology and, lastly, that current evaluation practices for lemmatization are not adequate to clearly discriminate between models.</abstract>
<identifier type="citekey">toporkov-agerri-2024-role</identifier>
<identifier type="doi">10.1162/coli_a_00497</identifier>
<location>
<url>https://aclanthology.org/2024.cl-1.6</url>
</location>
<part>
<date>2024-03</date>
<detail type="volume"><number>50</number></detail>
<detail type="issue"><number>1</number></detail>
<extent unit="page">
<start>157</start>
<end>191</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T On the Role of Morphological Information for Contextual Lemmatization
%A Toporkov, Olia
%A Agerri, Rodrigo
%J Computational Linguistics
%D 2024
%8 March
%V 50
%N 1
%I MIT Press
%C Cambridge, MA
%F toporkov-agerri-2024-role
%X Lemmatization is a natural language processing (NLP) task that consists of producing, from a given inflected word, its canonical form or lemma. Lemmatization is one of the basic tasks that facilitate downstream NLP applications, and is of particular importance for high-inflected languages. Given that the process to obtain a lemma from an inflected word can be explained by looking at its morphosyntactic category, including fine-grained morphosyntactic information to train contextual lemmatizers has become common practice, without considering whether that is the optimum in terms of downstream performance. In order to address this issue, in this article we empirically investigate the role of morphological information to develop contextual lemmatizers in six languages within a varied spectrum of morphological complexity: Basque, Turkish, Russian, Czech, Spanish, and English. Furthermore, and unlike the vast majority of previous work, we also evaluate lemmatizers in out-of-domain settings, which constitutes, after all, their most common application use. The results of our study are rather surprising. It turns out that providing lemmatizers with fine-grained morphological features during training is not that beneficial, not even for agglutinative languages. In fact, modern contextual word representations seem to implicitly encode enough morphological information to obtain competitive contextual lemmatizers without seeing any explicit morphological signal. Moreover, our experiments suggest that the best lemmatizers out-of-domain are those using simple UPOS tags or those trained without morphology and, lastly, that current evaluation practices for lemmatization are not adequate to clearly discriminate between models.
%R 10.1162/coli_a_00497
%U https://aclanthology.org/2024.cl-1.6
%U https://doi.org/10.1162/coli_a_00497
%P 157-191
Markdown (Informal)
[On the Role of Morphological Information for Contextual Lemmatization](https://aclanthology.org/2024.cl-1.6) (Toporkov & Agerri, CL 2024)
ACL