@inproceedings{saunack-etal-2021-low,
title = "How low is too low? A monolingual take on lemmatisation in {I}ndian languages",
author = "Saunack, Kumar and
Saurav, Kumar and
Bhattacharyya, Pushpak",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.322/",
doi = "10.18653/v1/2021.naacl-main.322",
pages = "4088--4094",
abstract = "Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Most prior work on ML based lemmatization has focused on high resource languages, where data sets (word forms) are readily available. For languages which have no linguistic work available, especially on morphology or in languages where the computational realization of linguistic rules is complex and cumbersome, machine learning based lemmatizers are the way togo. In this paper, we devote our attention to lemmatisation for low resource, morphologically rich scheduled Indian languages using neural methods. Here, low resource means only a small number of word forms are available. We perform tests to analyse the variance in monolingual models' performance on varying the corpus size and contextual morphological tag data for training. We show that monolingual approaches with data augmentation can give competitive accuracy even in the low resource setting, which augurs well for NLP in low resource setting."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saunack-etal-2021-low">
<titleInfo>
<title>How low is too low? A monolingual take on lemmatisation in Indian languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kumar</namePart>
<namePart type="family">Saunack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kumar</namePart>
<namePart type="family">Saurav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</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 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Most prior work on ML based lemmatization has focused on high resource languages, where data sets (word forms) are readily available. For languages which have no linguistic work available, especially on morphology or in languages where the computational realization of linguistic rules is complex and cumbersome, machine learning based lemmatizers are the way togo. In this paper, we devote our attention to lemmatisation for low resource, morphologically rich scheduled Indian languages using neural methods. Here, low resource means only a small number of word forms are available. We perform tests to analyse the variance in monolingual models’ performance on varying the corpus size and contextual morphological tag data for training. We show that monolingual approaches with data augmentation can give competitive accuracy even in the low resource setting, which augurs well for NLP in low resource setting.</abstract>
<identifier type="citekey">saunack-etal-2021-low</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.322</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.322/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>4088</start>
<end>4094</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How low is too low? A monolingual take on lemmatisation in Indian languages
%A Saunack, Kumar
%A Saurav, Kumar
%A Bhattacharyya, Pushpak
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F saunack-etal-2021-low
%X Lemmatization aims to reduce the sparse data problem by relating the inflected forms of a word to its dictionary form. Most prior work on ML based lemmatization has focused on high resource languages, where data sets (word forms) are readily available. For languages which have no linguistic work available, especially on morphology or in languages where the computational realization of linguistic rules is complex and cumbersome, machine learning based lemmatizers are the way togo. In this paper, we devote our attention to lemmatisation for low resource, morphologically rich scheduled Indian languages using neural methods. Here, low resource means only a small number of word forms are available. We perform tests to analyse the variance in monolingual models’ performance on varying the corpus size and contextual morphological tag data for training. We show that monolingual approaches with data augmentation can give competitive accuracy even in the low resource setting, which augurs well for NLP in low resource setting.
%R 10.18653/v1/2021.naacl-main.322
%U https://aclanthology.org/2021.naacl-main.322/
%U https://doi.org/10.18653/v1/2021.naacl-main.322
%P 4088-4094
Markdown (Informal)
[How low is too low? A monolingual take on lemmatisation in Indian languages](https://aclanthology.org/2021.naacl-main.322/) (Saunack et al., NAACL 2021)
ACL