Contrasting Syntagmatic and Paradigmatic Relations: Insights from Distributional Semantic Models

Abstract

This paper presents a large-scale evaluation of bag-of-words distributional models on two datasets from priming experiments involving syntagmatic and paradigmatic relations. We interpret the variation in performance achieved by different settings of the model parameters as an indication of which aspects of distributional patterns characterize these types of relations. Contrary to what has been argued in the literature In particular, our results show that size of the context window and dimensionality reduction play a key role in differentiating DSM performance on paradigmatic vs. syntagmatic relations.

Ähnliche Arbeiten