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.
This paper presents hypotheses on how chatbots function in problem-solving conversations, arguing that LLMs encode artificial metaphorical problem propagations and cannot match human cognitive flexibility, aligning with Yann LeCun's views.