@inproceedings{goldman-tsarfaty-2021-well,
title = "Well-Defined Morphology is Sentence-Level Morphology",
author = "Goldman, Omer and
Tsarfaty, Reut",
editor = "Ataman, Duygu and
Birch, Alexandra and
Conneau, Alexis and
Firat, Orhan and
Ruder, Sebastian and
Sahin, Gozde Gul",
booktitle = "Proceedings of the 1st Workshop on Multilingual Representation Learning",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.mrl-1.23/",
doi = "10.18653/v1/2021.mrl-1.23",
pages = "248--250",
abstract = "Morphological tasks have gained decent popularity within the NLP community in the recent years, with large multi-lingual datasets providing morphological analysis of words, either in or out of context. However, the lack of a clear linguistic definition for words destines the annotative work to be incomplete and mired in inconsistencies, especially cross-linguistically. In this work we expand morphological inflection of words to inflection of sentences to provide true universality disconnected from orthographic traditions of white-space usage. To allow annotation for sentence-inflection we define a morphological annotation scheme by a fixed set of inflectional features. We present a small cross-linguistic dataset including semi-manually generated simple sentences in 4 typologically diverse languages annotated according to our suggested scheme, and show that the task of reinflection gets substantially more difficult but that the change of scope from words to well-defined sentences allows interface with contextualized language models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goldman-tsarfaty-2021-well">
<titleInfo>
<title>Well-Defined Morphology is Sentence-Level Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Goldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multilingual Representation Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Duygu</namePart>
<namePart type="family">Ataman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Conneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orhan</namePart>
<namePart type="family">Firat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gozde</namePart>
<namePart type="given">Gul</namePart>
<namePart type="family">Sahin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>Morphological tasks have gained decent popularity within the NLP community in the recent years, with large multi-lingual datasets providing morphological analysis of words, either in or out of context. However, the lack of a clear linguistic definition for words destines the annotative work to be incomplete and mired in inconsistencies, especially cross-linguistically. In this work we expand morphological inflection of words to inflection of sentences to provide true universality disconnected from orthographic traditions of white-space usage. To allow annotation for sentence-inflection we define a morphological annotation scheme by a fixed set of inflectional features. We present a small cross-linguistic dataset including semi-manually generated simple sentences in 4 typologically diverse languages annotated according to our suggested scheme, and show that the task of reinflection gets substantially more difficult but that the change of scope from words to well-defined sentences allows interface with contextualized language models.</abstract>
<identifier type="citekey">goldman-tsarfaty-2021-well</identifier>
<identifier type="doi">10.18653/v1/2021.mrl-1.23</identifier>
<location>
<url>https://aclanthology.org/2021.mrl-1.23/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>248</start>
<end>250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Well-Defined Morphology is Sentence-Level Morphology
%A Goldman, Omer
%A Tsarfaty, Reut
%Y Ataman, Duygu
%Y Birch, Alexandra
%Y Conneau, Alexis
%Y Firat, Orhan
%Y Ruder, Sebastian
%Y Sahin, Gozde Gul
%S Proceedings of the 1st Workshop on Multilingual Representation Learning
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F goldman-tsarfaty-2021-well
%X Morphological tasks have gained decent popularity within the NLP community in the recent years, with large multi-lingual datasets providing morphological analysis of words, either in or out of context. However, the lack of a clear linguistic definition for words destines the annotative work to be incomplete and mired in inconsistencies, especially cross-linguistically. In this work we expand morphological inflection of words to inflection of sentences to provide true universality disconnected from orthographic traditions of white-space usage. To allow annotation for sentence-inflection we define a morphological annotation scheme by a fixed set of inflectional features. We present a small cross-linguistic dataset including semi-manually generated simple sentences in 4 typologically diverse languages annotated according to our suggested scheme, and show that the task of reinflection gets substantially more difficult but that the change of scope from words to well-defined sentences allows interface with contextualized language models.
%R 10.18653/v1/2021.mrl-1.23
%U https://aclanthology.org/2021.mrl-1.23/
%U https://doi.org/10.18653/v1/2021.mrl-1.23
%P 248-250
Markdown (Informal)
[Well-Defined Morphology is Sentence-Level Morphology](https://aclanthology.org/2021.mrl-1.23/) (Goldman & Tsarfaty, MRL 2021)
ACL