@inproceedings{gamba-zeman-2023-latin,
title = "{L}atin Morphology through the Centuries: Ensuring Consistency for Better Language Processing",
author = "Gamba, Federica and
Zeman, Daniel",
editor = "Anderson, Adam and
Gordin, Shai and
Li, Bin and
Liu, Yudong and
Passarotti, Marco C.",
booktitle = "Proceedings of the Ancient Language Processing Workshop",
month = sep,
year = "2023",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2023.alp-1.7",
pages = "59--67",
abstract = "This paper focuses on the process of harmonising the five Latin treebanks available in Universal Dependencies with respect to morphological annotation. We propose a workflow that allows to first spot inconsistencies and missing information, in order to detect to what extent the annotations differ, and then correct the retrieved bugs, with the goal of equalising the annotation of morphological features in the treebanks and producing more consistent linguistic data. Subsequently, we present some experiments carried out with UDPipe and Stanza in order to assess the impact of such harmonisation on parsing accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gamba-zeman-2023-latin">
<titleInfo>
<title>Latin Morphology through the Centuries: Ensuring Consistency for Better Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Federica</namePart>
<namePart type="family">Gamba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Zeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ancient Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Anderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shai</namePart>
<namePart type="family">Gordin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yudong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper focuses on the process of harmonising the five Latin treebanks available in Universal Dependencies with respect to morphological annotation. We propose a workflow that allows to first spot inconsistencies and missing information, in order to detect to what extent the annotations differ, and then correct the retrieved bugs, with the goal of equalising the annotation of morphological features in the treebanks and producing more consistent linguistic data. Subsequently, we present some experiments carried out with UDPipe and Stanza in order to assess the impact of such harmonisation on parsing accuracy.</abstract>
<identifier type="citekey">gamba-zeman-2023-latin</identifier>
<location>
<url>https://aclanthology.org/2023.alp-1.7</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>59</start>
<end>67</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Latin Morphology through the Centuries: Ensuring Consistency for Better Language Processing
%A Gamba, Federica
%A Zeman, Daniel
%Y Anderson, Adam
%Y Gordin, Shai
%Y Li, Bin
%Y Liu, Yudong
%Y Passarotti, Marco C.
%S Proceedings of the Ancient Language Processing Workshop
%D 2023
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F gamba-zeman-2023-latin
%X This paper focuses on the process of harmonising the five Latin treebanks available in Universal Dependencies with respect to morphological annotation. We propose a workflow that allows to first spot inconsistencies and missing information, in order to detect to what extent the annotations differ, and then correct the retrieved bugs, with the goal of equalising the annotation of morphological features in the treebanks and producing more consistent linguistic data. Subsequently, we present some experiments carried out with UDPipe and Stanza in order to assess the impact of such harmonisation on parsing accuracy.
%U https://aclanthology.org/2023.alp-1.7
%P 59-67
Markdown (Informal)
[Latin Morphology through the Centuries: Ensuring Consistency for Better Language Processing](https://aclanthology.org/2023.alp-1.7) (Gamba & Zeman, ALP-WS 2023)
ACL