@inproceedings{sahala-lincke-2025-neural,
title = "Neural Models for Lemmatization and {POS}-Tagging of Earlier and Late {E}gyptian (Supporting Hieroglyphic Input) and Demotic",
author = "Sahala, Aleksi and
Lincke, Eliese-Sophia",
editor = "Anderson, Adam and
Gordin, Shai and
Li, Bin and
Liu, Yudong and
Passarotti, Marco C. and
Sprugnoli, Rachele",
booktitle = "Proceedings of the Second Workshop on Ancient Language Processing",
month = may,
year = "2025",
address = "The Albuquerque Convention Center, Laguna",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.alp-1.12/",
doi = "10.18653/v1/2025.alp-1.12",
pages = "99--104",
ISBN = "979-8-89176-235-0",
abstract = "We present updated models for BabyLemma-tizer for lemmatizing and POS-tagging De-motic, Late Egyptian and Earlier Egyptian with a support for using hieroglyphs as an input. In this paper, we also use data that has not been cleaned from breakages. We achieve consistent UPOS tagging accuracy of 94{\%} or higher and an XPOS tagging accuracy of 93{\%} and higher for all languages. For lemmatization, which is challenging in all of our test languages due to extensive ambiguity, we demonstrate accu-racies from 77{\%} up to 92{\%} depending on the language and the input script."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sahala-lincke-2025-neural">
<titleInfo>
<title>Neural Models for Lemmatization and POS-Tagging of Earlier and Late Egyptian (Supporting Hieroglyphic Input) and Demotic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aleksi</namePart>
<namePart type="family">Sahala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eliese-Sophia</namePart>
<namePart type="family">Lincke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Ancient Language Processing</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>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">The Albuquerque Convention Center, Laguna</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-235-0</identifier>
</relatedItem>
<abstract>We present updated models for BabyLemma-tizer for lemmatizing and POS-tagging De-motic, Late Egyptian and Earlier Egyptian with a support for using hieroglyphs as an input. In this paper, we also use data that has not been cleaned from breakages. We achieve consistent UPOS tagging accuracy of 94% or higher and an XPOS tagging accuracy of 93% and higher for all languages. For lemmatization, which is challenging in all of our test languages due to extensive ambiguity, we demonstrate accu-racies from 77% up to 92% depending on the language and the input script.</abstract>
<identifier type="citekey">sahala-lincke-2025-neural</identifier>
<identifier type="doi">10.18653/v1/2025.alp-1.12</identifier>
<location>
<url>https://aclanthology.org/2025.alp-1.12/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>99</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Models for Lemmatization and POS-Tagging of Earlier and Late Egyptian (Supporting Hieroglyphic Input) and Demotic
%A Sahala, Aleksi
%A Lincke, Eliese-Sophia
%Y Anderson, Adam
%Y Gordin, Shai
%Y Li, Bin
%Y Liu, Yudong
%Y Passarotti, Marco C.
%Y Sprugnoli, Rachele
%S Proceedings of the Second Workshop on Ancient Language Processing
%D 2025
%8 May
%I Association for Computational Linguistics
%C The Albuquerque Convention Center, Laguna
%@ 979-8-89176-235-0
%F sahala-lincke-2025-neural
%X We present updated models for BabyLemma-tizer for lemmatizing and POS-tagging De-motic, Late Egyptian and Earlier Egyptian with a support for using hieroglyphs as an input. In this paper, we also use data that has not been cleaned from breakages. We achieve consistent UPOS tagging accuracy of 94% or higher and an XPOS tagging accuracy of 93% and higher for all languages. For lemmatization, which is challenging in all of our test languages due to extensive ambiguity, we demonstrate accu-racies from 77% up to 92% depending on the language and the input script.
%R 10.18653/v1/2025.alp-1.12
%U https://aclanthology.org/2025.alp-1.12/
%U https://doi.org/10.18653/v1/2025.alp-1.12
%P 99-104
Markdown (Informal)
[Neural Models for Lemmatization and POS-Tagging of Earlier and Late Egyptian (Supporting Hieroglyphic Input) and Demotic](https://aclanthology.org/2025.alp-1.12/) (Sahala & Lincke, ALP 2025)
ACL