@inproceedings{mccarthy-etal-2018-marrying,
title = "Marrying {U}niversal {D}ependencies and {U}niversal {M}orphology",
author = "McCarthy, Arya D. and
Silfverberg, Miikka and
Cotterell, Ryan and
Hulden, Mans and
Yarowsky, David",
editor = "de Marneffe, Marie-Catherine and
Lynn, Teresa and
Schuster, Sebastian",
booktitle = "Proceedings of the Second Workshop on Universal Dependencies ({UDW} 2018)",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6011",
doi = "10.18653/v1/W18-6011",
pages = "91--101",
abstract = "The Universal Dependencies (UD) and Universal Morphology (UniMorph) projects each present schemata for annotating the morphosyntactic details of language. Each project also provides corpora of annotated text in many languages{---}UD at the token level and UniMorph at the type level. As each corpus is built by different annotators, language-specific decisions hinder the goal of universal schemata. With compatibility of tags, each project{'}s annotations could be used to validate the other{'}s. Additionally, the availability of both type- and token-level resources would be a boon to tasks such as parsing and homograph disambiguation. To ease this interoperability, we present a deterministic mapping from Universal Dependencies v2 features into the UniMorph schema. We validate our approach by lookup in the UniMorph corpora and find a macro-average of 64.13{\%} recall. We also note incompatibilities due to paucity of data on either side. Finally, we present a critical evaluation of the foundations, strengths, and weaknesses of the two annotation projects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mccarthy-etal-2018-marrying">
<titleInfo>
<title>Marrying Universal Dependencies and Universal Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arya</namePart>
<namePart type="given">D</namePart>
<namePart type="family">McCarthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miikka</namePart>
<namePart type="family">Silfverberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mans</namePart>
<namePart type="family">Hulden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Yarowsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teresa</namePart>
<namePart type="family">Lynn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Schuster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Universal Dependencies (UD) and Universal Morphology (UniMorph) projects each present schemata for annotating the morphosyntactic details of language. Each project also provides corpora of annotated text in many languages—UD at the token level and UniMorph at the type level. As each corpus is built by different annotators, language-specific decisions hinder the goal of universal schemata. With compatibility of tags, each project’s annotations could be used to validate the other’s. Additionally, the availability of both type- and token-level resources would be a boon to tasks such as parsing and homograph disambiguation. To ease this interoperability, we present a deterministic mapping from Universal Dependencies v2 features into the UniMorph schema. We validate our approach by lookup in the UniMorph corpora and find a macro-average of 64.13% recall. We also note incompatibilities due to paucity of data on either side. Finally, we present a critical evaluation of the foundations, strengths, and weaknesses of the two annotation projects.</abstract>
<identifier type="citekey">mccarthy-etal-2018-marrying</identifier>
<identifier type="doi">10.18653/v1/W18-6011</identifier>
<location>
<url>https://aclanthology.org/W18-6011</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>91</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Marrying Universal Dependencies and Universal Morphology
%A McCarthy, Arya D.
%A Silfverberg, Miikka
%A Cotterell, Ryan
%A Hulden, Mans
%A Yarowsky, David
%Y de Marneffe, Marie-Catherine
%Y Lynn, Teresa
%Y Schuster, Sebastian
%S Proceedings of the Second Workshop on Universal Dependencies (UDW 2018)
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F mccarthy-etal-2018-marrying
%X The Universal Dependencies (UD) and Universal Morphology (UniMorph) projects each present schemata for annotating the morphosyntactic details of language. Each project also provides corpora of annotated text in many languages—UD at the token level and UniMorph at the type level. As each corpus is built by different annotators, language-specific decisions hinder the goal of universal schemata. With compatibility of tags, each project’s annotations could be used to validate the other’s. Additionally, the availability of both type- and token-level resources would be a boon to tasks such as parsing and homograph disambiguation. To ease this interoperability, we present a deterministic mapping from Universal Dependencies v2 features into the UniMorph schema. We validate our approach by lookup in the UniMorph corpora and find a macro-average of 64.13% recall. We also note incompatibilities due to paucity of data on either side. Finally, we present a critical evaluation of the foundations, strengths, and weaknesses of the two annotation projects.
%R 10.18653/v1/W18-6011
%U https://aclanthology.org/W18-6011
%U https://doi.org/10.18653/v1/W18-6011
%P 91-101
Markdown (Informal)
[Marrying Universal Dependencies and Universal Morphology](https://aclanthology.org/W18-6011) (McCarthy et al., UDW 2018)
ACL
- Arya D. McCarthy, Miikka Silfverberg, Ryan Cotterell, Mans Hulden, and David Yarowsky. 2018. Marrying Universal Dependencies and Universal Morphology. In Proceedings of the Second Workshop on Universal Dependencies (UDW 2018), pages 91–101, Brussels, Belgium. Association for Computational Linguistics.