@inproceedings{schmitt-constant-2019-neural,
title = "Neural Lemmatization of Multiword Expressions",
author = "Schmitt, Marine and
Constant, Mathieu",
editor = "Savary, Agata and
Escart{\'\i}n, Carla Parra and
Bond, Francis and
Mitrovi{\'c}, Jelena and
Mititelu, Verginica Barbu",
booktitle = "Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5117",
doi = "10.18653/v1/W19-5117",
pages = "142--148",
abstract = "This article focuses on the lemmatization of multiword expressions (MWEs). We propose a deep encoder-decoder architecture generating for every MWE word its corresponding part in the lemma, based on the internal context of the MWE. The encoder relies on recurrent networks based on (1) the character sequence of the individual words to capture their morphological properties, and (2) the word sequence of the MWE to capture lexical and syntactic properties. The decoder in charge of generating the corresponding part of the lemma for each word of the MWE is based on a classical character-level attention-based recurrent model. Our model is evaluated for Italian, French, Polish and Portuguese and shows good performances except for Polish.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schmitt-constant-2019-neural">
<titleInfo>
<title>Neural Lemmatization of Multiword Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Schmitt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Constant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Savary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelena</namePart>
<namePart type="family">Mitrović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verginica</namePart>
<namePart type="given">Barbu</namePart>
<namePart type="family">Mititelu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article focuses on the lemmatization of multiword expressions (MWEs). We propose a deep encoder-decoder architecture generating for every MWE word its corresponding part in the lemma, based on the internal context of the MWE. The encoder relies on recurrent networks based on (1) the character sequence of the individual words to capture their morphological properties, and (2) the word sequence of the MWE to capture lexical and syntactic properties. The decoder in charge of generating the corresponding part of the lemma for each word of the MWE is based on a classical character-level attention-based recurrent model. Our model is evaluated for Italian, French, Polish and Portuguese and shows good performances except for Polish.</abstract>
<identifier type="citekey">schmitt-constant-2019-neural</identifier>
<identifier type="doi">10.18653/v1/W19-5117</identifier>
<location>
<url>https://aclanthology.org/W19-5117</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>142</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Lemmatization of Multiword Expressions
%A Schmitt, Marine
%A Constant, Mathieu
%Y Savary, Agata
%Y Escartín, Carla Parra
%Y Bond, Francis
%Y Mitrović, Jelena
%Y Mititelu, Verginica Barbu
%S Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F schmitt-constant-2019-neural
%X This article focuses on the lemmatization of multiword expressions (MWEs). We propose a deep encoder-decoder architecture generating for every MWE word its corresponding part in the lemma, based on the internal context of the MWE. The encoder relies on recurrent networks based on (1) the character sequence of the individual words to capture their morphological properties, and (2) the word sequence of the MWE to capture lexical and syntactic properties. The decoder in charge of generating the corresponding part of the lemma for each word of the MWE is based on a classical character-level attention-based recurrent model. Our model is evaluated for Italian, French, Polish and Portuguese and shows good performances except for Polish.
%R 10.18653/v1/W19-5117
%U https://aclanthology.org/W19-5117
%U https://doi.org/10.18653/v1/W19-5117
%P 142-148
Markdown (Informal)
[Neural Lemmatization of Multiword Expressions](https://aclanthology.org/W19-5117) (Schmitt & Constant, MWE 2019)
ACL
- Marine Schmitt and Mathieu Constant. 2019. Neural Lemmatization of Multiword Expressions. In Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019), pages 142–148, Florence, Italy. Association for Computational Linguistics.