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

TL;DR

This paper investigates the signals that influence the classification of light verb constructions in Turkish, comparing various models and input features to understand what drives their detection and the role of morphology and lexical cues.

Contribution

It systematically analyzes the impact of lemma, morphosyntax, and full input models on LVC classification, highlighting the importance of normalization and lexical identity.

Findings

Coarse morphosyntax alone is insufficient for robust detection.

Lexical identity supports LVC judgments but is sensitive to normalization.

Lemma-only representations depend critically on normalization choices.

Abstract

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.