@inproceedings{dereza-etal-2024-findings,
title = "Findings of the {SIGTYP} 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages",
author = "Dereza, Oksana and
Doyle, Adrian and
Rani, Priya and
Ojha, Atul Kr. and
Moran, P{\'a}draic and
McCrae, John",
editor = "Hahn, Michael and
Sorokin, Alexey and
Kumar, Ritesh and
Shcherbakov, Andreas and
Otmakhova, Yulia and
Yang, Jinrui and
Serikov, Oleg and
Rani, Priya and
Ponti, Edoardo M. and
Murado{\u{g}}lu, Saliha and
Gao, Rena and
Cotterell, Ryan and
Vylomova, Ekaterina",
booktitle = "Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
month = mar,
year = "2024",
address = "St. Julian's, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigtyp-1.19",
pages = "160--172",
abstract = "This paper discusses the organisation and findings of the SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages. The shared task was split into the constrained and unconstrained tracks and involved solving either 3 or 5 problems for either 13 or 16 ancient and historical languages belonging to 4 language families, and making use of 6 different scripts. There were 14 registrations in total, of which 3 teams submitted to each track. Out of these 6 submissions, 2 systems were successful in the constrained setting and another 2 in the uncon- strained setting, and 4 system description papers were submitted by different teams. The best average result for morphological feature prediction was about 96{\%}, while the best average results for POS-tagging and lemmatisation were 96{\%} and 94{\%} respectively. At the word level, the winning team could not achieve a higher average accuracy across all 16 languages than 5.95{\%}, which demonstrates the difficulty of this problem. At the character level, the best average result over 16 languages 55.62{\%}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dereza-etal-2024-findings">
<titleInfo>
<title>Findings of the SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oksana</namePart>
<namePart type="family">Dereza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="family">Doyle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priya</namePart>
<namePart type="family">Rani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pádraic</namePart>
<namePart type="family">Moran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">McCrae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexey</namePart>
<namePart type="family">Sorokin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Shcherbakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Otmakhova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinrui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleg</namePart>
<namePart type="family">Serikov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priya</namePart>
<namePart type="family">Rani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saliha</namePart>
<namePart type="family">Muradoğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rena</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper discusses the organisation and findings of the SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages. The shared task was split into the constrained and unconstrained tracks and involved solving either 3 or 5 problems for either 13 or 16 ancient and historical languages belonging to 4 language families, and making use of 6 different scripts. There were 14 registrations in total, of which 3 teams submitted to each track. Out of these 6 submissions, 2 systems were successful in the constrained setting and another 2 in the uncon- strained setting, and 4 system description papers were submitted by different teams. The best average result for morphological feature prediction was about 96%, while the best average results for POS-tagging and lemmatisation were 96% and 94% respectively. At the word level, the winning team could not achieve a higher average accuracy across all 16 languages than 5.95%, which demonstrates the difficulty of this problem. At the character level, the best average result over 16 languages 55.62%</abstract>
<identifier type="citekey">dereza-etal-2024-findings</identifier>
<location>
<url>https://aclanthology.org/2024.sigtyp-1.19</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>160</start>
<end>172</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Findings of the SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages
%A Dereza, Oksana
%A Doyle, Adrian
%A Rani, Priya
%A Ojha, Atul Kr.
%A Moran, Pádraic
%A McCrae, John
%Y Hahn, Michael
%Y Sorokin, Alexey
%Y Kumar, Ritesh
%Y Shcherbakov, Andreas
%Y Otmakhova, Yulia
%Y Yang, Jinrui
%Y Serikov, Oleg
%Y Rani, Priya
%Y Ponti, Edoardo M.
%Y Muradoğlu, Saliha
%Y Gao, Rena
%Y Cotterell, Ryan
%Y Vylomova, Ekaterina
%S Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F dereza-etal-2024-findings
%X This paper discusses the organisation and findings of the SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages. The shared task was split into the constrained and unconstrained tracks and involved solving either 3 or 5 problems for either 13 or 16 ancient and historical languages belonging to 4 language families, and making use of 6 different scripts. There were 14 registrations in total, of which 3 teams submitted to each track. Out of these 6 submissions, 2 systems were successful in the constrained setting and another 2 in the uncon- strained setting, and 4 system description papers were submitted by different teams. The best average result for morphological feature prediction was about 96%, while the best average results for POS-tagging and lemmatisation were 96% and 94% respectively. At the word level, the winning team could not achieve a higher average accuracy across all 16 languages than 5.95%, which demonstrates the difficulty of this problem. At the character level, the best average result over 16 languages 55.62%
%U https://aclanthology.org/2024.sigtyp-1.19
%P 160-172
Markdown (Informal)
[Findings of the SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages](https://aclanthology.org/2024.sigtyp-1.19) (Dereza et al., SIGTYP-WS 2024)
ACL