Search for: All records

Grammar induction, the task of learning a set of syntactic rules from minimally annotated training data, provides a means of exploring the longstanding question of whether humans rely on innate knowledge to acquire language. Of the various formalisms available for grammar induction, categorial grammars provide an appealing option due to their transparent interface between syntax and semantics. However, to obtain competitive results, previous categorial grammar inducers have relied on shortcuts such as part-of-speech annotations or an ad hoc bias term in the objective function to ensure desirable branching behavior. We present a categorial grammar inducer that eliminates both shortcuts: it learns from raw data, and does not rely on a biased objective function. This improvement is achieved through a novel stochastic process used to select the set of available syntactic categories. On a corpus of English child-directed speech, the model attains a recall-homogeneity of 0.48, a large improvement over previous categorial grammar inducers. 

Abstract This article evaluates the predictions of an algorithmic‐level distributed associative memory model as it introduces, propagates, and resolves ambiguity, and compares it to the predictions of computational‐level parallel parsing models in which ambiguous analyses are accounted separately in discrete distributions. By superposing activation patterns that serve as cues to other activation patterns, the model is able to maintain multiple syntactically complex analyses superposed in a finite working memory, propagate this ambiguity through multiple intervening words, then resolve this ambiguity in a way that produces a measurable predictor that is proportional to the log conditional probability of the disambiguating word given its context, marginalizing over all remaining analyses. The results are indeed consistent in cases of complex structural ambiguity with computational‐level parallel parsing models producing this same probability as a predictor, which have been shown reliably to predict human reading times. 

Abstract This work presents a linguistic analysis into why larger Transformer-based pre-trained language models with more parameters and lower perplexity nonetheless yield surprisal estimates that are less predictive of human reading times. First, regression analyses show a strictly monotonic, positive log-linear relationship between perplexity and fit to reading times for the more recently released five GPT-Neo variants and eight OPT variants on two separate datasets, replicating earlier results limited to just GPT-2 (Oh et al., 2022). Subsequently, analysis of residual errors reveals a systematic deviation of the larger variants, such as underpredicting reading times of named entities and making compensatory overpredictions for reading times of function words such as modals and conjunctions. These results suggest that the propensity of larger Transformer-based models to ‘memorize’ sequences during training makes their surprisal estimates diverge from humanlike expectations, which warrants caution in using pre-trained language models to study human language processing. 

Expectation-based theories of sentence processing posit that processing difficulty is determined by predictability in context. While predictability quantified via surprisal has gained empirical support, this representation-agnostic measure leaves open the question of how to best approximate the human comprehender's latent probability model. This article first describes an incremental left-corner parser that incorporates information about common linguistic abstractions such as syntactic categories, predicate-argument structure, and morphological rules as a computational-level model of sentence processing. The article then evaluates a variety of structural parsers and deep neural language models as cognitive models of sentence processing by comparing the predictive power of their surprisal estimates on self-paced reading, eye-tracking, and fMRI data collected during real-time language processing. The results show that surprisal estimates from the proposed left-corner processing model deliver comparable and often superior fits to self-paced reading and eye-tracking data when compared to those from neural language models trained on much more data. This may suggest that the strong linguistic generalizations made by the proposed processing model may help predict humanlike processing costs that manifest in latency-based measures, even when the amount of training data is limited. Additionally, experiments using Transformer-based language models sharing the same primary architecture and training data show a surprising negative correlation between parameter count and fit to self-paced reading and eye-tracking data. These findings suggest that large-scale neural language models are making weaker generalizations based on patterns of lexical items rather than stronger, more humanlike generalizations based on linguistic structure.