@inproceedings{pommeret-etal-2026-thivlvc,
title = "{THIVLVC}: Retrieval Augmented Dependency Parsing for {L}atin",
author = "Pommeret, Luc and
Wagret, Thibault and
Deret, Jules",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages ({LT}4{HALA} 2026) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.lt4hala-1.20/",
doi = "10.63317/2q8twojtotyb",
pages = "219--225",
abstract = "We describe THIVLVC, a two-stage system for the EvaLatin 2026 Dependency Parsing task. Given a Latin sentence, we retrieve structurally similar entries from the CIRCSE treebank using sentence length and POS $n$-gram similarity, then prompt a large language model to refine the baseline parse from UDPipe using the retrieved examples and UD annotation guidelines. We submit two configurations: one without retrieval and one with retrieval (RAG). On poetry (Seneca), THIVLVC improves CLAS by +17 points over the UDPipe baseline; on prose (Thomas Aquinas), the gain is +1.5 CLAS. A double-blind error analysis of 300 divergences between our system and the gold standard reveals that, among unanimous annotator decisions, 53.3{\%} favour THIVLVC, showing annotation inconsistencies both within and across treebanks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pommeret-etal-2026-thivlvc">
<titleInfo>
<title>THIVLVC: Retrieval Augmented Dependency Parsing for Latin</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luc</namePart>
<namePart type="family">Pommeret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thibault</namePart>
<namePart type="family">Wagret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jules</namePart>
<namePart type="family">Deret</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 Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026</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 Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe THIVLVC, a two-stage system for the EvaLatin 2026 Dependency Parsing task. Given a Latin sentence, we retrieve structurally similar entries from the CIRCSE treebank using sentence length and POS n-gram similarity, then prompt a large language model to refine the baseline parse from UDPipe using the retrieved examples and UD annotation guidelines. We submit two configurations: one without retrieval and one with retrieval (RAG). On poetry (Seneca), THIVLVC improves CLAS by +17 points over the UDPipe baseline; on prose (Thomas Aquinas), the gain is +1.5 CLAS. A double-blind error analysis of 300 divergences between our system and the gold standard reveals that, among unanimous annotator decisions, 53.3% favour THIVLVC, showing annotation inconsistencies both within and across treebanks.</abstract>
<identifier type="citekey">pommeret-etal-2026-thivlvc</identifier>
<identifier type="doi">10.63317/2q8twojtotyb</identifier>
<location>
<url>https://aclanthology.org/2026.lt4hala-1.20/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>219</start>
<end>225</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T THIVLVC: Retrieval Augmented Dependency Parsing for Latin
%A Pommeret, Luc
%A Wagret, Thibault
%A Deret, Jules
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F pommeret-etal-2026-thivlvc
%X We describe THIVLVC, a two-stage system for the EvaLatin 2026 Dependency Parsing task. Given a Latin sentence, we retrieve structurally similar entries from the CIRCSE treebank using sentence length and POS n-gram similarity, then prompt a large language model to refine the baseline parse from UDPipe using the retrieved examples and UD annotation guidelines. We submit two configurations: one without retrieval and one with retrieval (RAG). On poetry (Seneca), THIVLVC improves CLAS by +17 points over the UDPipe baseline; on prose (Thomas Aquinas), the gain is +1.5 CLAS. A double-blind error analysis of 300 divergences between our system and the gold standard reveals that, among unanimous annotator decisions, 53.3% favour THIVLVC, showing annotation inconsistencies both within and across treebanks.
%R 10.63317/2q8twojtotyb
%U https://aclanthology.org/2026.lt4hala-1.20/
%U https://doi.org/10.63317/2q8twojtotyb
%P 219-225
Markdown (Informal)
[THIVLVC: Retrieval Augmented Dependency Parsing for Latin](https://aclanthology.org/2026.lt4hala-1.20/) (Pommeret et al., LT4HALA 2026)
ACL
- Luc Pommeret, Thibault Wagret, and Jules Deret. 2026. THIVLVC: Retrieval Augmented Dependency Parsing for Latin. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 219–225, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).