@inproceedings{huang-2026-semantic,
title = "Semantic Alignment across {A}ncient {E}gyptian Language Stages via Normalization-Aware Multitask Learning",
author = "Huang, He",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.702/",
doi = "10.63317/3v9kjvq9f3qp",
pages = "8923--8936",
abstract = "We study word-level semantic alignment across four historical stages of Ancient Egyptian. These stages differ in script and orthography, and parallel data are scarce. We jointly train a compact encoder-decoder model with a shared byte-level tokenizer on all four stages, combining masked language modeling (MLM), translation language modeling (TLM), sequence-to-sequence translation, and part-of-speech tagging under a task-aware loss with fixed weights and uncertainty-based scaling. To reduce surface divergence we add Latin transliteration and IPA reconstruction as auxiliary views. We integrate these views through KL-based consistency and through embedding-level fusion. We evaluate alignment quality using pairwise metrics, specifically ROC-AUC and triplet accuracy, on curated Egyptian{--}English and intra-Egyptian cognate datasets. Translation yields the strongest gains. IPA with KL consistency improves cross-branch alignment, while early fusion demonstrates limited efficacy. Although the overall alignment remains limited, the findings provide a reproducible baseline and practical guidance for modeling historical languages under real constraints. They also show how normalization and task design shape what counts as alignment in typologically distant settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-2026-semantic">
<titleInfo>
<title>Semantic Alignment across Ancient Egyptian Language Stages via Normalization-Aware Multitask Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study word-level semantic alignment across four historical stages of Ancient Egyptian. These stages differ in script and orthography, and parallel data are scarce. We jointly train a compact encoder-decoder model with a shared byte-level tokenizer on all four stages, combining masked language modeling (MLM), translation language modeling (TLM), sequence-to-sequence translation, and part-of-speech tagging under a task-aware loss with fixed weights and uncertainty-based scaling. To reduce surface divergence we add Latin transliteration and IPA reconstruction as auxiliary views. We integrate these views through KL-based consistency and through embedding-level fusion. We evaluate alignment quality using pairwise metrics, specifically ROC-AUC and triplet accuracy, on curated Egyptian–English and intra-Egyptian cognate datasets. Translation yields the strongest gains. IPA with KL consistency improves cross-branch alignment, while early fusion demonstrates limited efficacy. Although the overall alignment remains limited, the findings provide a reproducible baseline and practical guidance for modeling historical languages under real constraints. They also show how normalization and task design shape what counts as alignment in typologically distant settings.</abstract>
<identifier type="citekey">huang-2026-semantic</identifier>
<identifier type="doi">10.63317/3v9kjvq9f3qp</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.702/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>8923</start>
<end>8936</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Alignment across Ancient Egyptian Language Stages via Normalization-Aware Multitask Learning
%A Huang, He
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F huang-2026-semantic
%X We study word-level semantic alignment across four historical stages of Ancient Egyptian. These stages differ in script and orthography, and parallel data are scarce. We jointly train a compact encoder-decoder model with a shared byte-level tokenizer on all four stages, combining masked language modeling (MLM), translation language modeling (TLM), sequence-to-sequence translation, and part-of-speech tagging under a task-aware loss with fixed weights and uncertainty-based scaling. To reduce surface divergence we add Latin transliteration and IPA reconstruction as auxiliary views. We integrate these views through KL-based consistency and through embedding-level fusion. We evaluate alignment quality using pairwise metrics, specifically ROC-AUC and triplet accuracy, on curated Egyptian–English and intra-Egyptian cognate datasets. Translation yields the strongest gains. IPA with KL consistency improves cross-branch alignment, while early fusion demonstrates limited efficacy. Although the overall alignment remains limited, the findings provide a reproducible baseline and practical guidance for modeling historical languages under real constraints. They also show how normalization and task design shape what counts as alignment in typologically distant settings.
%R 10.63317/3v9kjvq9f3qp
%U https://aclanthology.org/2026.lrec-1.702/
%U https://doi.org/10.63317/3v9kjvq9f3qp
%P 8923-8936
Markdown (Informal)
[Semantic Alignment across Ancient Egyptian Language Stages via Normalization-Aware Multitask Learning](https://aclanthology.org/2026.lrec-1.702/) (Huang, LREC 2026)
ACL