This study examines the influence of lexical frequency bias and selectional constraints on the resolution of complement ambiguity during sentence processing. Some argue that in complement ambiguity resolution, lexical frequency bias and selectional constraints lead to the clausal complement before disambiguation, while others claim that the nominal complement is maintained until the disambiguating verb appears. The present study investigates this issue in two reading experiments using a temporal adjunct. The results suggested the rapid influence of lexical frequency bias and selectional constraints. However, the temporal adjunct introduces a bias towards the nominal complement, and ultimately overrides the influence of the lexical frequency bias and selectional constraints. These results suggest that processing preferences dynamically change, influenced by multiple biases.

This study investigates cue-based memory retrieval during sentence processing. Cue-based retrieval theories argue that the parser uses lexical and structural information as retrieval cues to retrieve items from memory. Evidence for cue-based memory retrieval comes from research showing that non-target representations matching retrieval cues interfere with target retrieval. However, the degree of susceptibility to this similarity-based interference has been debated, having led to the development of different computational models. This study focuses on two cue-based models and tests their predictions in two experiments. The results suggested similarity-based interference, but its patterns were not fully compatible with these models. To reconcile these findings within the framework of cue-based memory retrieval, this paper presents a model that assigns substantial weight to the structure-based cue and incorporates the notions of initial retrieval and revision. Results from simulations indicate that the model incorporating these assumptions provides a better fit to the observed data.

This study investigates the representation of garden-path sentences and its interaction with memory retrieval. Garden-path sentences are initially misanalysed, and the initial misrepresentations tend to affect language comprehension, even after revision. Memory retrieval targets items in memory based on their representations. Our main research question investigates whether memory retrieval targets initial misrepresentations or revised representations in garden-path sentences. Using the cue-based memory retrieval model, we generated predictions for potential processing patterns stemming from this research question. The experiments used lexicality maze, self-paced reading, and offline comprehension questions. The results showed largely similar processing patterns between garden-path and non-garden-path sentences, suggesting that initial misrepresentations do not affect memory retrieval.