LAUSR

Abstract A range of studies investigating how overspecified referring expressions (e.g., the stripy cup to describe a single cup) affect referent identification have found it to slow identification, speed it up, or yield no effect on processing speed. To date, these studies have all used adjectives that are semantically arbitrary within the sentential context. In addition to the standard ‘informativeness’ design that manipulates the presence of contrast sets, we controlled the semantic relevance of adjectives in discourse to reveal whether overspecifying adjectives would affect processing when relevant to the context (fed the hungry rabbit) compared to when they are not (tickled the hungry rabbit). Using a self-paced reading paradigm with a sample of adult participants (N = 31), we found that overspecified noun phrases were read more slowly than those that distinguished a member of a contrast set. Importantly, this penalty was mitigated when adjectives were semantically relevant. Contrary to classical approaches, we show that modifiers do not necessarily presuppose a set, and that referential and semantic information is integrated rapidly in pragmatic processing. Our data support Fukumura and van Gompel's (2017) meaning-based redundancy hypothesis, which predicts that it is the specific semantic representation of the overspecifying adjective that determines whether a penalty is incurred, rather than generic Gricean expectations. We extend this account using a novel experimental design.