@inproceedings{bergmanis-goldwater-2018-context,
title = "Context Sensitive Neural Lemmatization with {L}ematus",
author = "Bergmanis, Toms and
Goldwater, Sharon",
editor = "Walker, Marilyn and
Ji, Heng and
Stent, Amanda",
booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)",
month = jun,
year = "2018",
address = "New Orleans, Louisiana",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N18-1126",
doi = "10.18653/v1/N18-1126",
pages = "1391--1400",
abstract = "The main motivation for developing contextsensitive lemmatizers is to improve performance on unseen and ambiguous words. Yet previous systems have not carefully evaluated whether the use of context actually helps in these cases. We introduce Lematus, a lemmatizer based on a standard encoder-decoder architecture, which incorporates character-level sentence context. We evaluate its lemmatization accuracy across 20 languages in both a full data setting and a lower-resource setting with 10k training examples in each language. In both settings, we show that including context significantly improves results against a context-free version of the model. Context helps more for ambiguous words than for unseen words, though the latter has a greater effect on overall performance differences between languages. We also compare to three previous context-sensitive lemmatization systems, which all use pre-extracted edit trees as well as hand-selected features and/or additional sources of information such as tagged training data. Without using any of these, our context-sensitive model outperforms the best competitor system (Lemming) in the fulldata setting, and performs on par in the lowerresource setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bergmanis-goldwater-2018-context">
<titleInfo>
<title>Context Sensitive Neural Lemmatization with Lematus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toms</namePart>
<namePart type="family">Bergmanis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharon</namePart>
<namePart type="family">Goldwater</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marilyn</namePart>
<namePart type="family">Walker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Stent</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Orleans, Louisiana</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The main motivation for developing contextsensitive lemmatizers is to improve performance on unseen and ambiguous words. Yet previous systems have not carefully evaluated whether the use of context actually helps in these cases. We introduce Lematus, a lemmatizer based on a standard encoder-decoder architecture, which incorporates character-level sentence context. We evaluate its lemmatization accuracy across 20 languages in both a full data setting and a lower-resource setting with 10k training examples in each language. In both settings, we show that including context significantly improves results against a context-free version of the model. Context helps more for ambiguous words than for unseen words, though the latter has a greater effect on overall performance differences between languages. We also compare to three previous context-sensitive lemmatization systems, which all use pre-extracted edit trees as well as hand-selected features and/or additional sources of information such as tagged training data. Without using any of these, our context-sensitive model outperforms the best competitor system (Lemming) in the fulldata setting, and performs on par in the lowerresource setting.</abstract>
<identifier type="citekey">bergmanis-goldwater-2018-context</identifier>
<identifier type="doi">10.18653/v1/N18-1126</identifier>
<location>
<url>https://aclanthology.org/N18-1126</url>
</location>
<part>
<date>2018-06</date>
<extent unit="page">
<start>1391</start>
<end>1400</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Context Sensitive Neural Lemmatization with Lematus
%A Bergmanis, Toms
%A Goldwater, Sharon
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F bergmanis-goldwater-2018-context
%X The main motivation for developing contextsensitive lemmatizers is to improve performance on unseen and ambiguous words. Yet previous systems have not carefully evaluated whether the use of context actually helps in these cases. We introduce Lematus, a lemmatizer based on a standard encoder-decoder architecture, which incorporates character-level sentence context. We evaluate its lemmatization accuracy across 20 languages in both a full data setting and a lower-resource setting with 10k training examples in each language. In both settings, we show that including context significantly improves results against a context-free version of the model. Context helps more for ambiguous words than for unseen words, though the latter has a greater effect on overall performance differences between languages. We also compare to three previous context-sensitive lemmatization systems, which all use pre-extracted edit trees as well as hand-selected features and/or additional sources of information such as tagged training data. Without using any of these, our context-sensitive model outperforms the best competitor system (Lemming) in the fulldata setting, and performs on par in the lowerresource setting.
%R 10.18653/v1/N18-1126
%U https://aclanthology.org/N18-1126
%U https://doi.org/10.18653/v1/N18-1126
%P 1391-1400
Markdown (Informal)
[Context Sensitive Neural Lemmatization with Lematus](https://aclanthology.org/N18-1126) (Bergmanis & Goldwater, NAACL 2018)
ACL
- Toms Bergmanis and Sharon Goldwater. 2018. Context Sensitive Neural Lemmatization with Lematus. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1391–1400, New Orleans, Louisiana. Association for Computational Linguistics.