@inproceedings{muradoglu-etal-2020-compress,
title = "To compress or not to compress? A Finite-State approach to {N}en verbal morphology",
author = "Muradoglu, Saliha and
Evans, Nicholas and
Suominen, Hanna",
editor = "Rijhwani, Shruti and
Liu, Jiangming and
Wang, Yizhong and
Dror, Rotem",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-srw.28",
doi = "10.18653/v1/2020.acl-srw.28",
pages = "207--213",
abstract = "This paper describes the development of a verbal morphological parser for an under-resourced Papuan language, Nen. Nen verbal morphology is particularly complex, with a transitive verb taking up to 1,740 unique features. The structural properties exhibited by Nen verbs raises interesting choices for analysis. Here we compare two possible methods of analysis: {`}Chunking{'} and decomposition. {`}Chunking{'} refers to the concept of collating morphological segments into one, whereas the decomposition model follows a more classical linguistic approach. Both models are built using the Finite-State Transducer toolkit foma. The resultant architecture shows differences in size and structural clarity. While the {`}Chunking{'} model is under half the size of the full de-composed counterpart, the decomposition displays higher structural order. In this paper, we describe the challenges encountered when modelling a language exhibiting distributed exponence and present the first morphological analyser for Nen, with an overall accuracy of 80.3{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muradoglu-etal-2020-compress">
<titleInfo>
<title>To compress or not to compress? A Finite-State approach to Nen verbal morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoglu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Evans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Suominen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiangming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yizhong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rotem</namePart>
<namePart type="family">Dror</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the development of a verbal morphological parser for an under-resourced Papuan language, Nen. Nen verbal morphology is particularly complex, with a transitive verb taking up to 1,740 unique features. The structural properties exhibited by Nen verbs raises interesting choices for analysis. Here we compare two possible methods of analysis: ‘Chunking’ and decomposition. ‘Chunking’ refers to the concept of collating morphological segments into one, whereas the decomposition model follows a more classical linguistic approach. Both models are built using the Finite-State Transducer toolkit foma. The resultant architecture shows differences in size and structural clarity. While the ‘Chunking’ model is under half the size of the full de-composed counterpart, the decomposition displays higher structural order. In this paper, we describe the challenges encountered when modelling a language exhibiting distributed exponence and present the first morphological analyser for Nen, with an overall accuracy of 80.3%.</abstract>
<identifier type="citekey">muradoglu-etal-2020-compress</identifier>
<identifier type="doi">10.18653/v1/2020.acl-srw.28</identifier>
<location>
<url>https://aclanthology.org/2020.acl-srw.28</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>207</start>
<end>213</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T To compress or not to compress? A Finite-State approach to Nen verbal morphology
%A Muradoglu, Saliha
%A Evans, Nicholas
%A Suominen, Hanna
%Y Rijhwani, Shruti
%Y Liu, Jiangming
%Y Wang, Yizhong
%Y Dror, Rotem
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F muradoglu-etal-2020-compress
%X This paper describes the development of a verbal morphological parser for an under-resourced Papuan language, Nen. Nen verbal morphology is particularly complex, with a transitive verb taking up to 1,740 unique features. The structural properties exhibited by Nen verbs raises interesting choices for analysis. Here we compare two possible methods of analysis: ‘Chunking’ and decomposition. ‘Chunking’ refers to the concept of collating morphological segments into one, whereas the decomposition model follows a more classical linguistic approach. Both models are built using the Finite-State Transducer toolkit foma. The resultant architecture shows differences in size and structural clarity. While the ‘Chunking’ model is under half the size of the full de-composed counterpart, the decomposition displays higher structural order. In this paper, we describe the challenges encountered when modelling a language exhibiting distributed exponence and present the first morphological analyser for Nen, with an overall accuracy of 80.3%.
%R 10.18653/v1/2020.acl-srw.28
%U https://aclanthology.org/2020.acl-srw.28
%U https://doi.org/10.18653/v1/2020.acl-srw.28
%P 207-213
Markdown (Informal)
[To compress or not to compress? A Finite-State approach to Nen verbal morphology](https://aclanthology.org/2020.acl-srw.28) (Muradoglu et al., ACL 2020)
ACL