@inproceedings{straka-etal-2024-ufal,
title = "{{\'U}FAL} {L}atin{P}ipe at {E}va{L}atin 2024: Morphosyntactic Analysis of {L}atin",
author = "Straka, Milan and
Strakov{\'a}, Jana and
Gamba, Federica",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lt4hala-1.24",
pages = "207--214",
abstract = "We present LatinPipe, the winning submission to the EvaLatin 2024 Dependency Parsing shared task. Our system consists of a fine-tuned concatenation of base and large pre-trained LMs, with a dot-product attention head for parsing and softmax classification heads for morphology to jointly learn both dependency parsing and morphological analysis. It is trained by sampling from seven publicly available Latin corpora, utilizing additional harmonization of annotations to achieve a more unified annotation style. Before fine-tuning, we train the system for a few initial epochs with frozen weights. We also add additional local relative contextualization by stacking the BiLSTM layers on top of the Transformer(s). Finally, we ensemble output probability distributions from seven randomly instantiated networks for the final submission. The code is available at https://github.com/ufal/evalatin2024-latinpipe.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="straka-etal-2024-ufal">
<titleInfo>
<title>ÚFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin</title>
</titleInfo>
<name type="personal">
<namePart type="given">Milan</namePart>
<namePart type="family">Straka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jana</namePart>
<namePart type="family">Straková</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federica</namePart>
<namePart type="family">Gamba</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 Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</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>We present LatinPipe, the winning submission to the EvaLatin 2024 Dependency Parsing shared task. Our system consists of a fine-tuned concatenation of base and large pre-trained LMs, with a dot-product attention head for parsing and softmax classification heads for morphology to jointly learn both dependency parsing and morphological analysis. It is trained by sampling from seven publicly available Latin corpora, utilizing additional harmonization of annotations to achieve a more unified annotation style. Before fine-tuning, we train the system for a few initial epochs with frozen weights. We also add additional local relative contextualization by stacking the BiLSTM layers on top of the Transformer(s). Finally, we ensemble output probability distributions from seven randomly instantiated networks for the final submission. The code is available at https://github.com/ufal/evalatin2024-latinpipe.</abstract>
<identifier type="citekey">straka-etal-2024-ufal</identifier>
<location>
<url>https://aclanthology.org/2024.lt4hala-1.24</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>207</start>
<end>214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ÚFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin
%A Straka, Milan
%A Straková, Jana
%A Gamba, Federica
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) @ LREC-COLING-2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F straka-etal-2024-ufal
%X We present LatinPipe, the winning submission to the EvaLatin 2024 Dependency Parsing shared task. Our system consists of a fine-tuned concatenation of base and large pre-trained LMs, with a dot-product attention head for parsing and softmax classification heads for morphology to jointly learn both dependency parsing and morphological analysis. It is trained by sampling from seven publicly available Latin corpora, utilizing additional harmonization of annotations to achieve a more unified annotation style. Before fine-tuning, we train the system for a few initial epochs with frozen weights. We also add additional local relative contextualization by stacking the BiLSTM layers on top of the Transformer(s). Finally, we ensemble output probability distributions from seven randomly instantiated networks for the final submission. The code is available at https://github.com/ufal/evalatin2024-latinpipe.
%U https://aclanthology.org/2024.lt4hala-1.24
%P 207-214
Markdown (Informal)
[ÚFAL LatinPipe at EvaLatin 2024: Morphosyntactic Analysis of Latin](https://aclanthology.org/2024.lt4hala-1.24) (Straka et al., LT4HALA-WS 2024)
ACL