THIVLVC: Retrieval Augmented Dependency Parsing for Latin

Luc Pommeret, Thibault Wagret, Jules Deret


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.
Anthology ID:
2026.lt4hala-1.20
Volume:
Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Rachele Sprugnoli, Marco Passarotti
Venues:
LT4HALA | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
219–225
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-lt4hala-20
DOI:
10.63317/2q8twojtotyb
Bibkey:
Cite (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).
Cite (Informal):
THIVLVC: Retrieval Augmented Dependency Parsing for Latin (Pommeret et al., LT4HALA 2026)
Copy Citation: