@inproceedings{swaelens-etal-2023-evaluating,
title = "Evaluating Existing Lemmatisers on Unedited Byzantine {G}reek Poetry",
author = "Swaelens, Colin and
De Vos, Ilse and
Lefever, Els",
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-1.13",
pages = "111--116",
abstract = "This paper reports on the results of a comparative evaluation in view of the development of a new lemmatizer for unedited, Byzantine Greek texts. For the experiment, the performance of four existing lemmatizers, all pre-trained on Ancient Greek texts, was evaluated on how well they could handle texts stemming from the Middle Ages and displaying quite some peculiarities. The aim of this study is to get insights into the pitfalls of existing lemmatistion approaches as well as the specific challenges of our Byzantine Greek corpus, in order to develop a lemmatizer that can cope with its peculiarities. The results of the experiment show an accuracy drop of 20pp. on our corpus, which is further investigated in a qualitative error analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="swaelens-etal-2023-evaluating">
<titleInfo>
<title>Evaluating Existing Lemmatisers on Unedited Byzantine Greek Poetry</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Swaelens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilse</namePart>
<namePart type="family">De Vos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</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 reports on the results of a comparative evaluation in view of the development of a new lemmatizer for unedited, Byzantine Greek texts. For the experiment, the performance of four existing lemmatizers, all pre-trained on Ancient Greek texts, was evaluated on how well they could handle texts stemming from the Middle Ages and displaying quite some peculiarities. The aim of this study is to get insights into the pitfalls of existing lemmatistion approaches as well as the specific challenges of our Byzantine Greek corpus, in order to develop a lemmatizer that can cope with its peculiarities. The results of the experiment show an accuracy drop of 20pp. on our corpus, which is further investigated in a qualitative error analysis.</abstract>
<identifier type="citekey">swaelens-etal-2023-evaluating</identifier>
<location>
<url>https://aclanthology.org/2023.alp-1.13</url>
</location>
<part>
<date>2023-09</date>
<extent unit="page">
<start>111</start>
<end>116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Existing Lemmatisers on Unedited Byzantine Greek Poetry
%A Swaelens, Colin
%A De Vos, Ilse
%A Lefever, Els
%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 swaelens-etal-2023-evaluating
%X This paper reports on the results of a comparative evaluation in view of the development of a new lemmatizer for unedited, Byzantine Greek texts. For the experiment, the performance of four existing lemmatizers, all pre-trained on Ancient Greek texts, was evaluated on how well they could handle texts stemming from the Middle Ages and displaying quite some peculiarities. The aim of this study is to get insights into the pitfalls of existing lemmatistion approaches as well as the specific challenges of our Byzantine Greek corpus, in order to develop a lemmatizer that can cope with its peculiarities. The results of the experiment show an accuracy drop of 20pp. on our corpus, which is further investigated in a qualitative error analysis.
%U https://aclanthology.org/2023.alp-1.13
%P 111-116
Markdown (Informal)
[Evaluating Existing Lemmatisers on Unedited Byzantine Greek Poetry](https://aclanthology.org/2023.alp-1.13) (Swaelens et al., ALP-WS 2023)
ACL