@article{ponti-etal-2019-modeling,
title = "Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing",
author = "Ponti, Edoardo Maria and
O{'}Horan, Helen and
Berzak, Yevgeni and
Vuli{\'c}, Ivan and
Reichart, Roi and
Poibeau, Thierry and
Shutova, Ekaterina and
Korhonen, Anna",
journal = "Computational Linguistics",
volume = "45",
number = "3",
month = sep,
year = "2019",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/J19-3005",
doi = "10.1162/coli_a_00357",
pages = "559--601",
abstract = "Linguistic typology aims to capture structural and semantic variation across the world{'}s languages. A large-scale typology could provide excellent guidance for multilingual Natural Language Processing (NLP), particularly for languages that suffer from the lack of human labeled resources. We present an extensive literature survey on the use of typological information in the development of NLP techniques. Our survey demonstrates that to date, the use of information in existing typological databases has resulted in consistent but modest improvements in system performance. We show that this is due to both intrinsic limitations of databases (in terms of coverage and feature granularity) and under-utilization of the typological features included in them. We advocate for a new approach that adapts the broad and discrete nature of typological categories to the contextual and continuous nature of machine learning algorithms used in contemporary NLP. In particular, we suggest that such an approach could be facilitated by recent developments in data-driven induction of typological knowledge.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ponti-etal-2019-modeling">
<titleInfo>
<title>Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">O’Horan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yevgeni</namePart>
<namePart type="family">Berzak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Poibeau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</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>Linguistic typology aims to capture structural and semantic variation across the world’s languages. A large-scale typology could provide excellent guidance for multilingual Natural Language Processing (NLP), particularly for languages that suffer from the lack of human labeled resources. We present an extensive literature survey on the use of typological information in the development of NLP techniques. Our survey demonstrates that to date, the use of information in existing typological databases has resulted in consistent but modest improvements in system performance. We show that this is due to both intrinsic limitations of databases (in terms of coverage and feature granularity) and under-utilization of the typological features included in them. We advocate for a new approach that adapts the broad and discrete nature of typological categories to the contextual and continuous nature of machine learning algorithms used in contemporary NLP. In particular, we suggest that such an approach could be facilitated by recent developments in data-driven induction of typological knowledge.</abstract>
<identifier type="citekey">ponti-etal-2019-modeling</identifier>
<identifier type="doi">10.1162/coli_a_00357</identifier>
<location>
<url>https://aclanthology.org/J19-3005</url>
</location>
<part>
<date>2019-09</date>
<detail type="volume"><number>45</number></detail>
<detail type="issue"><number>3</number></detail>
<extent unit="page">
<start>559</start>
<end>601</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
%A Ponti, Edoardo Maria
%A O’Horan, Helen
%A Berzak, Yevgeni
%A Vulić, Ivan
%A Reichart, Roi
%A Poibeau, Thierry
%A Shutova, Ekaterina
%A Korhonen, Anna
%J Computational Linguistics
%D 2019
%8 September
%V 45
%N 3
%I MIT Press
%C Cambridge, MA
%F ponti-etal-2019-modeling
%X Linguistic typology aims to capture structural and semantic variation across the world’s languages. A large-scale typology could provide excellent guidance for multilingual Natural Language Processing (NLP), particularly for languages that suffer from the lack of human labeled resources. We present an extensive literature survey on the use of typological information in the development of NLP techniques. Our survey demonstrates that to date, the use of information in existing typological databases has resulted in consistent but modest improvements in system performance. We show that this is due to both intrinsic limitations of databases (in terms of coverage and feature granularity) and under-utilization of the typological features included in them. We advocate for a new approach that adapts the broad and discrete nature of typological categories to the contextual and continuous nature of machine learning algorithms used in contemporary NLP. In particular, we suggest that such an approach could be facilitated by recent developments in data-driven induction of typological knowledge.
%R 10.1162/coli_a_00357
%U https://aclanthology.org/J19-3005
%U https://doi.org/10.1162/coli_a_00357
%P 559-601
Markdown (Informal)
[Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing](https://aclanthology.org/J19-3005) (Ponti et al., CL 2019)
ACL