@inproceedings{miranda-2024-allen,
title = "{A}llen Institute for {AI} @ {SIGTYP} 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages",
author = "Miranda, Lester James",
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-1.18",
pages = "151--159",
abstract = "In this paper, we describe Allen AI{'}s submission to the constrained track of the SIGTYP 2024 Shared Task. Using only the data provided by the organizers, we pretrained a transformer-based multilingual model, then finetuned it on the Universal Dependencies (UD) annotations of a given language for a downstream task. Our systems achieved decent performance on the test set, beating the baseline in most language-task pairs, yet struggles with subtoken tags in multiword expressions as seen in Coptic and Ancient Hebrew. On the validation set, we obtained {\mbox{$\geq$}}70{\%} F1- score on most language-task pairs. In addition, we also explored the cross-lingual capability of our trained models. This paper highlights our pretraining and finetuning process, and our findings from our internal evaluations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miranda-2024-allen">
<titleInfo>
<title>Allen Institute for AI @ SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lester</namePart>
<namePart type="given">James</namePart>
<namePart type="family">Miranda</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>In this paper, we describe Allen AI’s submission to the constrained track of the SIGTYP 2024 Shared Task. Using only the data provided by the organizers, we pretrained a transformer-based multilingual model, then finetuned it on the Universal Dependencies (UD) annotations of a given language for a downstream task. Our systems achieved decent performance on the test set, beating the baseline in most language-task pairs, yet struggles with subtoken tags in multiword expressions as seen in Coptic and Ancient Hebrew. On the validation set, we obtained \geq70% F1- score on most language-task pairs. In addition, we also explored the cross-lingual capability of our trained models. This paper highlights our pretraining and finetuning process, and our findings from our internal evaluations.</abstract>
<identifier type="citekey">miranda-2024-allen</identifier>
<location>
<url>https://aclanthology.org/2024.sigtyp-1.18</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>151</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Allen Institute for AI @ SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages
%A Miranda, Lester James
%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 miranda-2024-allen
%X In this paper, we describe Allen AI’s submission to the constrained track of the SIGTYP 2024 Shared Task. Using only the data provided by the organizers, we pretrained a transformer-based multilingual model, then finetuned it on the Universal Dependencies (UD) annotations of a given language for a downstream task. Our systems achieved decent performance on the test set, beating the baseline in most language-task pairs, yet struggles with subtoken tags in multiword expressions as seen in Coptic and Ancient Hebrew. On the validation set, we obtained \geq70% F1- score on most language-task pairs. In addition, we also explored the cross-lingual capability of our trained models. This paper highlights our pretraining and finetuning process, and our findings from our internal evaluations.
%U https://aclanthology.org/2024.sigtyp-1.18
%P 151-159
Markdown (Informal)
[Allen Institute for AI @ SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages](https://aclanthology.org/2024.sigtyp-1.18) (Miranda, SIGTYP-WS 2024)
ACL