Tag
This paper presents an interpretable network-based framework for representing idiomatic expressions across eight languages using binary conceptual features. Community detection reveals that idioms cluster by conceptual schema rather than language, and the framework improves downstream idiom detection and cross-lingual transfer over embedding-based baselines.
Introduces IdioLink, a retrieval benchmark of 10,700 documents and 2,140 queries across 107 idioms that tests whether models can link idiomatic expressions to conceptually equivalent literal or paraphrased meanings. Evaluations show current embedding models struggle with this task, highlighting gaps in idiom-aware semantic retrieval.