@inproceedings{swaelens-etal-2024-lemmatisation-medieval,
title = "Lemmatisation of Medieval {G}reek: Against the Limits of Transformer{'}s Capabilities?",
author = "Swaelens, Colin and
Singh, Pranaydeep and
de Vos, Ilse and
Lefever, Els",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.899",
pages = "10293--10302",
abstract = "This paper presents preliminary experiments for the lemmatisation of unedited, Byzantine Greek epigrams. This type of Greek is quite different from its classical ancestor, mostly because of its orthographic inconsistencies. Existing lemmatisation algorithms display an accuracy drop of around 30pp when tested on these Byzantine book epigrams. We conducted seven different lemmatisation experiments, which were either transformer-based or based on neural edit-trees. The best performing lemmatiser was a hybrid method combining transformer-based embeddings with a dictionary look-up. We compare our results with existing lemmatisers, and provide a detailed error analysis revealing why unedited, Byzantine Greek is so challenging for lemmatisation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="swaelens-etal-2024-lemmatisation-medieval">
<titleInfo>
<title>Lemmatisation of Medieval Greek: Against the Limits of Transformer’s Capabilities?</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">Pranaydeep</namePart>
<namePart type="family">Singh</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>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents preliminary experiments for the lemmatisation of unedited, Byzantine Greek epigrams. This type of Greek is quite different from its classical ancestor, mostly because of its orthographic inconsistencies. Existing lemmatisation algorithms display an accuracy drop of around 30pp when tested on these Byzantine book epigrams. We conducted seven different lemmatisation experiments, which were either transformer-based or based on neural edit-trees. The best performing lemmatiser was a hybrid method combining transformer-based embeddings with a dictionary look-up. We compare our results with existing lemmatisers, and provide a detailed error analysis revealing why unedited, Byzantine Greek is so challenging for lemmatisation.</abstract>
<identifier type="citekey">swaelens-etal-2024-lemmatisation-medieval</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.899</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10293</start>
<end>10302</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lemmatisation of Medieval Greek: Against the Limits of Transformer’s Capabilities?
%A Swaelens, Colin
%A Singh, Pranaydeep
%A de Vos, Ilse
%A Lefever, Els
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F swaelens-etal-2024-lemmatisation-medieval
%X This paper presents preliminary experiments for the lemmatisation of unedited, Byzantine Greek epigrams. This type of Greek is quite different from its classical ancestor, mostly because of its orthographic inconsistencies. Existing lemmatisation algorithms display an accuracy drop of around 30pp when tested on these Byzantine book epigrams. We conducted seven different lemmatisation experiments, which were either transformer-based or based on neural edit-trees. The best performing lemmatiser was a hybrid method combining transformer-based embeddings with a dictionary look-up. We compare our results with existing lemmatisers, and provide a detailed error analysis revealing why unedited, Byzantine Greek is so challenging for lemmatisation.
%U https://aclanthology.org/2024.lrec-main.899
%P 10293-10302
Markdown (Informal)
[Lemmatisation of Medieval Greek: Against the Limits of Transformer’s Capabilities?](https://aclanthology.org/2024.lrec-main.899) (Swaelens et al., LREC-COLING 2024)
ACL