Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.05564 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908942097973248 |
|---|---|
| author | Pommeret, Luc Wagret, Thibault Deret, Jules |
| author_facet | Pommeret, Luc Wagret, Thibault Deret, Jules |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05564 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | THIVLVC: Retrieval Augmented Dependency Parsing for Latin Pommeret, Luc Wagret, Thibault Deret, Jules Computation and Language 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. |
| title | THIVLVC: Retrieval Augmented Dependency Parsing for Latin |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.05564 |