跳到正文
arXiv cs.CL· Julian Schelb, Michael Wittweiler, Marie Revellio·· 2 天前AI 评分18

用少量标注学习拉丁文学文本复用中的词级解释

Learning Word-Level Explanations of Text Reuse in Latin Literature with Little Annotation

AI 导读

研究提出一种只需少量标注的方法,为拉丁文学文本复用对逐词标注操作类型(复制、词形变化、替换等):先用已知操作作用于拉丁文本生成合成对训练初始模型,再用主动学习挑选待人工修正的样本。

正文 · 原文

View PDF HTML (experimental)

Abstract:Detecting an intertextual reference is only the first step; philologists also need to know how a later author reworked the source. We explain a reuse pair word by word: each word of the reusing passage is first aligned to its source word, then labeled with the operation that transformed it, such as a copy, a change of inflection, or a substitution. Such word-level operations are expensive to annotate, and only a few corpora annotated at this level exist for text reuse in Latin literature. We describe a procedure that needs only a limited number of annotations: synthetic pairs, built by applying known operations to Latin text, train a first model, and active learning chooses the pairs an annotator corrects. Among several architectures, a model that links and labels together performs best: a pointer network that, for every reuse word, chooses a source word and names the operation in the same step. We show that with active learning, 200 pairs chosen by uncertainty are enough for the model to match one trained on every annotated pair of the 1,490 references of the Loci Similes benchmark. We release our code, word-level predictions for all references, and an interactive demo.
Comments: 18 pages, 5 figures, 8 tables. Code: this https URL Demo: this https URL
Subjects: Computation and Language (cs.CL)
Cite as: arXiv:2611.18319 [cs.CL]
  (or arXiv:2611.18319v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2611.18319

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Julian Schelb [view email]
[v1] Fri, 13 Nov 2026 15:33:43 UTC (1,005 KB)

来源:arXiv cs.CL · arxiv.org