Superlatives in Context: Explicit and Implicit Domain Restrictions for Superlative Frames

Superlatives are used to single out elements with a <PRE_TAG>maximal/minimal property</POST_TAG>. Semantically, <PRE_TAG>superlatives</POST_TAG> perform a set comparison: something (or some things) has the min/max property out of a set. As such, <PRE_TAG>superlatives</POST_TAG> provide an ideal phenomenon for studying <PRE_TAG>implicit phenomena</POST_TAG> and discourse restrictions. While this comparison set is often not explicitly defined, its (implicit) restrictions can be inferred from the discourse context the expression appears in. In this work we provide an extensive computational study on the semantics of <PRE_TAG>superlatives</POST_TAG>. We propose a unified account of <PRE_TAG>superlative semantics</POST_TAG> which allows us to derive a broad-coverage annotation schema. Using this unified schema we annotated a multi-domain dataset of <PRE_TAG>superlatives</POST_TAG> and their semantic interpretations. We specifically focus on interpreting implicit or ambiguous superlative expressions, by analyzing how the discourse context restricts the set of interpretations. In a set of experiments we then analyze how well models perform at variations of predicting superlative semantics, with and without context. We show that the fine-grained semantics of <PRE_TAG>superlatives</POST_TAG> in context can be challenging for contemporary models, including GPT-4.