A model of plausibility

Plausibility has been implicated as playing a critical role in many cognitive phenomena from comprehension to problem solving. Yet, across cognitive science, plausibility is usually treated as an operationalized variable or metric rather than being explained or studied in itself. This article describes a new cognitive model of plausibility, the Plausibility Analysis Model (PAM), which is aimed at modeling human plausibility judgment. This model uses commonsense knowledge of concept-coherence to determine the degree of plausibility of a target scenario. In essence, a highly plausible scenario is one that fits prior knowledge well: with many different sources of corroboration, without complexity of explanation, and with minimal conjecture. A detailed simulation of empirical plausibility findings is reported, which shows a close correspondence between the model and human judgments. In addition, a sensitivity analysis demonstrates that PAM is robust in its operations.     

Examining the evidence for an independent semantic analyzer: an ERP study in Spanish

Recent ERP findings challenge the widespread assumption that syntactic and semantic processes are tightly coupled. Syntactically well-formed sentences that are semantically anomalous due to thematic mismatches elicit a P600, the component standardly associated with syntactic anomaly. This ‘thematic P600’ effect has been attributed to detection of semantically plausible thematic relations that conflict with the surface syntactic structure of the sentence, implying a processing architecture with an independent semantic analyzer. A key finding is that the P600 is selectively sensitive to the presence of plausible verb-argument relations, and that otherwise an N400 is elicited (The hearty meal was devouring … vs. The dusty tabletop was devouring …: Kim & Osterhout, 2005). The current study investigates in Spanish whether the evidence for an independent semantic analyzer is better explained by a standard architecture that rapidly integrates multiple sources of lexical, syntactic, and semantic information. The study manipulated the presence of plausible thematic relations, and varied the choice of auxiliary between passive-biased fue and active-progressive biased estaba. Results show a late positivity that appeared as soon as comprehenders detected an improbable combination of subject animacy, auxiliary bias, or verb voice morphology. This effect appeared at the lexical verb in the fue conditions and at the auxiliary in the estaba conditions. The late positivity elicited by surface thematic anomalies was the same, regardless of the presence of a plausible non-surface interpretation, and no N400 effects were elicited. These findings do not implicate an independent semantic analyzer, and are compatible with standard language processing architectures.     

Parametric effects of syntactic-semantic conflict in Broca's area during sentence processing

The hypothesized role of Broca’s area in sentence processing ranges from domain-general executive function to domain-specific computation that is specific to certain syntactic structures. We examined this issue by manipulating syntactic structure and conflict between syntactic and semantic cues in a sentence processing task. Functional neuroimaging revealed that activation within several Broca’s area regions of interest reflected the parametric variation in syntactic-semantic conflict. These results suggest that Broca’s area supports sentence processing by mediating between multiple incompatible constraints on sentence interpretation, consistent with this area’s well-known role in conflict resolution in other linguistic and non-linguistic tasks.     

Uncertainty about the rest of the sentence

A word-by-word human sentence processing complexity metric is presented. This metric formalizes the intuition that comprehenders have more trouble on words contributing larger amounts of information about the syntactic structure of the sentence as a whole. The formalization is in terms of the conditional entropy of grammatical continuations, given the words that have been heard so far. To calculate the predictions of this metric, Wilson and Carroll's (1954) original entropy reduction idea is extended to infinite languages. This is demonstrated with a mildly context-sensitive language that includes relative clauses formed on a variety of grammatical relations across the Accessibility Hierarchy of Keenan and Comrie (1977). Predictions are derived that correlate significantly with repetition accuracy results obtained in a sentence-memory experiment (Keenan & Hawkins, 1987).     

Interpretation-based processing: a unified theory of semantic sentence comprehension

We present interpretation-based processing—a theory of sentence processing that builds a syntactic and a semantic representation for a sentence and assigns an interpretation to the sentence as soon as possible. That interpretation can further participate in comprehension and in lexical processing and is vital for relating the sentence to the prior discourse. Our theory offers a unified account of the processing of literal sentences, metaphoric sentences, and sentences containing semantic illusions. It also explains how text can prime lexical access. We show that word literality is a matter of degree and that the speed and quality of comprehension depend both on how similar words are to their antecedents in the preceding text and how salient the sentence is with respect to the preceding text. Interpretation-based processing also reconciles superficially contradictory findings about the difference in processing times for metaphors and literals. The theory has been implemented in ACT-R [Anderson and Lebiere, The Atomic Components of Thought, Lawrence Erlbaum Associates Publishers, Mahwah, NJ, 1998].     

An activation-based model of sentence processing as skilled memory retrieval

We present a detailed process theory of the moment-by-moment working-memory retrievals and associated control structure that subserve sentence comprehension. The theory is derived from the application of independently motivated principles of memory and cognitive skill to the specialized task of sentence parsing. The resulting theory construes sentence processing as a series of skilled associative memory retrievals modulated by similarity-based interference and fluctuating activation. The cognitive principles are formalized in computational form in the Adaptive Control of Thought–Rational (ACT–R) architecture, and our process model is realized in ACT–R. We present the results of 6 sets of simulations: 5 simulation sets provide quantitative accounts of the effects of length and structural interference on both unambiguous and garden-path structures. A final simulation set provides a graded taxonomy of double center embeddings ranging from relatively easy to extremely difficult. The explanation of center-embedding difficulty is a novel one that derives from the model' complete reliance on discriminating retrieval cues in the absence of an explicit representation of serial order information. All fits were obtained with only 1 free scaling parameter fixed across the simulations; all other parameters were ACT–R defaults. The modeling results support the hypothesis that fluctuating activation and similarity-based interference are the key factors shaping working memory in sentence processing. We contrast the theory and empirical predictions with several related accounts of sentence-processing complexity.     

Spatial and linguistic aspects of visual imagery in sentence comprehension

There is mounting evidence that language comprehension involves the activation of mental imagery of the content of utterances ( Barsalou, 1999 ; Bergen, Chang, & Narayan, 2004 ; Bergen, Narayan, & Feldman, 2003 ; Narayan, Bergen, & Weinberg, 2004 ; Richardson, Spivey, McRae, & Barsalou, 2003 ; Stanfield & Zwaan, 2001 ; Zwaan, Stanfield, & Yaxley, 2002 ). This imagery can have motor or perceptual content. Three main questions about the process remain under‐explored, however. First, are lexical associations with perception or motion sufficient to yield mental simulation, or is the integration of lexical semantics into larger structures, like sentences, necessary? Second, what linguistic elements (e.g., verbs, nouns, etc.) trigger mental simulations? Third, how detailed are the visual simulations that are performed? A series of behavioral experiments address these questions, using a visual object categorization task to investigate whether up‐ or down‐related language selectively interferes with visual processing in the same part of the visual field (following Richardson et al., 2003 ). The results demonstrate that either subject nouns or main verbs can trigger visual imagery, but only when used in literal sentences about real space—metaphorical language does not yield significant effects—which implies that it is the comprehension of the sentence as a whole and not simply lexical associations that yields imagery effects. These studies also show that the evoked imagery contains detail as to the part of the visual field where the described scene would take place.     

Higher-order activity beyond the word level: cortical dynamics of simple transitive sentence comprehension

Slow electrophysiological effects, which fluctuate throughout the course of a sentence, independent of transient responses to individual words, have been reported. However, this type of activity has scarcely been studied, and with only limited use of electrophysiological information, so that the brain areas in which these variations originate have not been clearly identified. To improve this state of affairs, a principal component analysis and a modern source analysis algorithm (LORETA) were applied to the slow activity underlying transitive sentence reading. Four components explained 97.3% of the variance. Of key interest was a slow variation that occurred throughout the entire sentence but peaked with the appearance of the verb. The main solution for this component was localized in prefrontal and temporal regions presumably involved in semantic sentence processing. This constitutes empirical evidence for cortical activity--related to semantic processes thought to be involved in thematic role assignment--developing throughout the sentence but presenting a conspicuous maximum with the appearance of the verb. This finding also highlights the central role of verb information in the understanding of transitive sentences.     

The thematic hierarchy in sentence comprehension: A study on the interaction between verb class and word order in Spanish

Linking is the theory that captures the mapping of the semantic roles of lexical arguments to the syntactic functions of the phrases that realize them. At the sentence level, linking allows us to understand “who did what to whom” in an event. In Spanish, linking has been shown to interact with word order, verb class, and case marking. The current study aims to provide the first piece of experimental evidence about the interplay between word order and verb type in Spanish. We achieve this by adopting role and reference grammar and the extended argument dependency model. Two different types of clauses were examined in a self-paced reading task: clauses with object–experiencer psychological verbs and activity verbs. These types of verbs differ in the way that their syntactic and semantic structures are linked, and thus they provide interesting evidence on how information that belongs to the syntax–semantics interface might influence the predictive and integrative processes of sentence comprehension with alternative word orders. Results indicate that in Spanish, comprehension and processing speed is enhanced when the order of the constituents in the sentence mirrors their ranking on a semantic hierarchy that encodes a verb's lexical semantics. Moreover, results show that during online comprehension, predictive mechanisms based on argument hierarchization are used rapidly to inform the processing system. Our findings corroborate already existing cross-linguistic evidence on the issue and are briefly discussed in the light of other sentence-processing models.     

A probabilistic model of melody perception

This study presents a probabilistic model of melody perception, which infers the key of a melody and also judges the probability of the melody itself. The model uses Bayesian reasoning: For any "surface" pattern and underlying "structure," we can infer the structure maximizing P (structure|surface) based on knowledge of P (surface, structure). The probability of the surface can then be calculated as ∑ P (surface, structure), summed over all structures. In this case, the surface is a pattern of notes; the structure is a key. A generative model is proposed, based on three principles: (a) melodies tend to remain within a narrow pitch range; (b) note-to-note intervals within a melody tend to be small; and (c) notes tend to conform to a distribution (or key profile) that depends on the key. The model is tested in three ways. First, it is tested on its ability to identify the keys of a set of folksong melodies. Second, it is tested on a melodic expectation task in which it must judge the probability of different notes occurring given a prior context; these judgments are compared with perception data from a melodic expectation experiment. Finally, the model is tested on its ability to detect incorrect notes in melodies by assigning them lower probabilities than the original versions.     

From exemplar to grammar: a probabilistic analogy-based model of language learning

While rules and exemplars are usually viewed as opposites, this paper argues that they form end points of the same distribution. By representing both rules and exemplars as (partial) trees, we can take into account the fluid middle ground between the two extremes. This insight is the starting point for a new theory of language learning that is based on the following idea: If a language learner does not know which phrase-structure trees should be assigned to initial sentences, s/he allows (implicitly) for all possible trees and lets linguistic experience decide which is the "best" tree for each sentence. The best tree is obtained by maximizing "structural analogy" between a sentence and previous sentences, which is formalized by the most probable shortest combination of subtrees from all trees of previous sentences. Corpus-based experiments with this model on the Penn Treebank and the Childes database indicate that it can learn both exemplar-based and rule-based aspects of language, ranging from phrasal verbs to auxiliary fronting. By having learned the syntactic structures of sentences, we have also learned the grammar implicit in these structures, which can in turn be used to produce new sentences. We show that our model mimicks children's language development from item-based constructions to abstract constructions, and that the model can simulate some of the errors made by children in producing complex questions.     

The influence of contextual contrast on syntactic processing: evidence for strong-interaction in sentence comprehension

The present study compares the processing of unambiguous restrictive and non-restrictive relative clauses (RCs) within both a null context and a supportive discourse using a self-paced reading methodology. Individuals read restrictive RCs more slowly than non-restrictive RCs in a null context, but processed restrictive RCs faster than non-restrictive RCs in supportive context, resulting in an interaction between context and RC type. These results provide evidence for two theoretical points. First, principles analogous to those in referential theory [Altmann G. T. M., & Steedman, M. (1988). Interaction with context during human sentence processing. Cognition, 30, 191-238; Crain, S., & Steedman, M. (1985). On not being led up the garden path: The use of context by the psychological parser. In D. Dowty, L. Karttunnen, A. Zwicky (Eds.), Natural language parsing. Cambridge, UK: Cambridge University Press] apply not only in resolving ambiguity but also in processing unambiguous sentences. Second, the discourse context can guide and facilitate interpretive processing. This result suggests that intrasentential factors such as syntax are not autonomous from contextual processing, contrary to the modularity hypothesis [Fodor, J. A. (1983). Modularity of mind. Cambridge, MA: MIT Press].     

Children’s (in)ability to recover from garden paths in a verb-final language: Evidence for developing control in sentence processing

An eye-tracking study explored Korean-speaking adults’ and 4- and 5-year-olds’ ability to recover from misinterpretations of temporarily ambiguous phrases during spoken language comprehension. Eye movement and action data indicated that children, but not adults, had difficulty in recovering from these misinterpretations despite strong disambiguating evidence at the end of the sentence. These findings are notable for their striking similarities with findings from children parsing English; however, in those and other studies of English, children were found to be reluctant to use late-arriving syntactic evidence to override earlier verb-based cues to structure, whereas here Korean children were reluctant to use late-arriving verb-based cues to override earlier syntactic evidence. The findings implicate a general cross-linguistic pattern for parsing development in which late-developing cognitive control abilities mediate the recovery from so-called “garden path” sentences. Children’s limited cognitive control prevents them from inhibiting misinterpretations even when the disambiguating evidence comes from highly informative verb information.     

Automatic perceptual simulation of first language meanings during second language sentence processing in bilinguals

Research supports the claim that, when understanding language, people perform mental simulation using those parts of the brain which support sensation, action, and emotion. A major criticism of the findings quoted as evidence for embodied simulation, however, is that they could be a result of conscious image generation strategies. Here we exploit the well-known fact that bilinguals routinely and automatically activate both their languages during comprehension to test whether this automatic process is, in turn, modulated by embodied simulatory processes. Dutch participants heard English sentences containing interlingual homophones and implying specific distance relations, and had to subsequently respond to pictures of objects matching or mismatching this implied distance. Participants were significantly slower to reject critical items when their perceptual features matched said distance relationship. These results suggest that bilinguals not only activate task-irrelevant meanings of interlingual homophones, but also automatically simulate these meanings in a detailed perceptual fashion. Our study supports the claim that embodied simulation is not due to participants' conscious strategies, but is an automatic component of meaning construction.     

The interpretation of classically quantified sentences: a set-theoretic approach

We present a set-theoretic model of the mental representation of classically quantified sentences (All P are Q, Some P are Q, Some P are not Q, and No P are Q). We take inclusion, exclusion, and their negations to be primitive concepts. We show that although these sentences are known to have a diagrammatic expression (in the form of the Gergonne circles) that constitutes a semantic representation, these concepts can also be expressed syntactically in the form of algebraic formulas. We hypothesized that the quantified sentences have an abstract underlying representation common to the formulas and their associated sets of diagrams (models). We derived 9 predictions (3 semantic, 2 pragmatic, and 4 mixed) regarding people's assessment of how well each of the 5 diagrams expresses the meaning of each of the quantified sentences. We report the results from 3 experiments using Gergonne's (1817) circles or an adaptation of Leibniz (1903/1988) lines as external representations and show them to support the predictions.     

Language and age effects in children's processing of word order

We compare the processing of transitive sentences in young learners of a strict word order language (English) and two languages that allow noun omissions and many variant word orders: Turkish, a case-marked language, and Mandarin Chinese, a non case-marked language. Children aged 1–3 years listened to simple transitive sentences in the typical word order of their language, paired with two visual scenes, only one of which matched the sentence. Multiple measures of comprehension (percent of looking to match, latency to look to match, number of switches of attention) revealed a general pattern of early sensitivity to word order, coupled with language and age effects in children's processing efficiency. In particular, English learners showed temporally speedier processing of transitive sentences than Turkish learners, who also displayed more uncertainty about the matching scene. Mandarin learners behaved like Turkish learners in showing slower processing of sentences, and all language groups displayed faster processing by older than younger children. These results demonstrate that sentence processing is sensitive to crosslinguistic features beginning early in language development.     

Gapping: Electrophysiological evidence for immediate processing of "missing" verbs in sentence comprehension

In the present study we use event related potentials (ERPs) to explore the time course of identification and resolution of verb gaps. ERPs were recorded while participants read sentences that contained a verb gap like Ron took/sanded the planks, and Bill ? the hammer... Plausibility of the critical words (hammer) that followed the verb gap was manipulated. Relative to the plausible control (preceded by took), ERPs to the critical word in the implausible condition (preceded by sanded) showed an N400, followed by a positivity (P600). ERPs to determiners following gapped verbs showed a negativity between 100 and 300 ms, and a positivity between 300 and 500 ms compared to determiners in non-gapping constructions. These results suggest that the sentence processor recognizes a verb gap and reconstructs the verb information at the earliest possible occasion, and that this reconstruction process is different from the reconstruction of antecedents in other filler-gap constructions (e.g., WH gaps).     

Hemispheric asymmetries in the split-fovea model of semantic processing

We report a series of neural network models of semantic processing of single English words in the left and the right hemispheres of the brain. We implement the foveal splitting of the visual field and assess the influence of this splitting on a mapping from orthography to semantic representations in single word reading. The models were trained on English four-letter words, presented according to their frequency in all positions encountered during normal reading. The architecture of the model interacted with the training set to produce processing asymmetries comparable to those found in behavioral studies. First, the cueing effects of dominant and subordinate meanings of ambiguous words were different for words presented to the left or to the right of the input layer. Second, priming effects of groups of related words were stronger in the left input than the right input of the model. These effects were caused by coarser-coding in the right half compared with the left half of the model, an emergent effect of the split model interacting with informational asymmetries in the left and right parts of words in the lexicon of English. Some or all of the behavioral data for reading single words in English may have a similar origin.     

The role of working memory in syntactic sentence realization: A modeling & simulation approach

This paper examines the effects of working memory size in incremental grammatical encoding during language production. Our experiment tests different variants of a computational-cognitive model that combines an empirically validated framework of general cognition, ACT-R, with a linguistic theory, Combinatory Categorial Grammar. The model is induced from a corpus of spoken dialogue. This methodology facilitates comparison of different strategies and working memory capacities according to the similarity of the model’s produced sentences to the corpus sentences. The experiment presented shows that while having more working memory available improves performance, using less working memory during realization does as well, even after controlling sentence length. Sentences realized with a more incremental strategy also appear to more closely track the naturalistic data. As high incrementality is correlated with low working memory usage, this study offers a possible mechanism by which syntactic incrementality can be explained. Finally, this paper proposes a multi-disciplinary modeling and simulation-based approach to empirical psycholinguistic inquiry.