arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.04127cs.CLcs.AI
收藏

从引理到依赖:哪些信号驱动轻动词分类?

From Lemmas to Dependencies: What Signals Drive Light Verbs Classification?

University of Chicago(芝加哥大学);Fırat University(费拉特大学)

Sercan Karakaş, Yusuf Şimşek

AI总结:

本文研究了土耳其语中轻动词分类的驱动因素,通过限制模型输入发现词汇身份和形态学语法对分类的影响,揭示了引理表示的依赖性。

摘要:

轻动词结构(LVCs)是一类具有挑战性的动词多词表达,尤其是在土耳其语中,丰富的形态学和产生活的复杂谓语会产生最小的idiomatic谓语意义与字面动词-论元用法之间的对比。本文询问是什么信号驱动LVC分类,通过系统地限制模型输入来实现。使用UD衍生的监督,我们比较了基于引理的基线(引理TF-IDF + 逻辑回归;BERTurk在引理序列上训练)、仅基于语法的逻辑回归(仅UD形态学语法,UPOS/DEPREL/MORPH),以及全输入BERTurk基线。我们在一个受控的诊断集上进行评估,使用随机负样本、词汇控制(NLVC)和LVC正样本,报告分割后的性能以暴露决策边界行为。结果表明,在受控对比下,粗略形态学语法本身不足以进行稳健的LVC检测,而词汇身份支持LVC判断,但对校准和归一化选择敏感。总体而言,我们的发现促使对土耳其MWEs的有针对性评估,并表明“仅引理”不是单一、明确的表示,而取决于归一化如何操作化。

英文摘要:

Light verb constructions (LVCs) are a challenging class of verbal multiword expressions, especially in Turkish, where rich morphology and productive complex predicates create minimal contrasts between idiomatic predicate meanings and literal verb--argument uses. This paper asks what signals drive LVC classification by systematically restricting model inputs. Using UD-derived supervision, we compare lemma-driven baselines (lemma TF--IDF + Logistic Regression; BERTurk trained on lemma sequences), a grammar-only Logistic Regression over UD morphosyntax (UPOS/DEPREL/MORPH), and a full-input BERTurk baseline. We evaluate on a controlled diagnostic set with Random negatives, lexical controls (NLVC), and LVC positives, reporting split-wise performance to expose decision-boundary behavior. Results show that coarse morphosyntax alone is insufficient for robust LVC detection under controlled contrasts, while lexical identity supports LVC judgments but is sensitive to calibration and normalization choices. Overall, Our findings motivate targeted evaluation of Turkish MWEs and show that ``lemma-only'' is not a single, well-defined representation, but one that depends critically on how normalization is operationalized.

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。

↑