THIVLVC:用于拉丁语的检索增强依存解析
THIVLVC: Retrieval Augmented Dependency Parsing for Latin
AI总结:
THIVLVC通过检索相似结构条目并利用大语言模型优化,提升了拉丁语依存解析的CLAS得分,尤其在诗歌部分表现更优。
摘要:
我们描述了THIVLVC,一种用于EvaLatin 2026依存解析任务的两阶段系统。给定一个拉丁语句子,我们通过句子长度和词性标注n-gram相似性从CIRCSE树库中检索结构相似的条目,然后提示大语言模型利用检索到的示例和UD标注指南优化基于UDPipe的基线解析。我们提交了两种配置:一种无检索和一种有检索(RAG)。在诗歌(塞涅卡)上,THIVLVC在UDPipe基线上提升了17个CLAS分数;在散文(托马斯·阿奎那)上,提升为1.5 CLAS。对300个与黄金标准不同的差异进行双盲错误分析发现,53.3%的统一标注员决策支持THIVLVC,显示了树库内和跨树库的标注不一致性。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。