Four experiments examined participants' ability to produce surface characteristics of sentences using an on-line story reading task. Participants read a series of stories in which either all, or the majority of sentences were written in the same "style," or surface form. Twice per story, participants were asked to fill in a blank consistent with the story. For sentences that contained three sty...

Motivated by both classroom needs and learning science questions, we developed two computer-based systems to help students learn the English article system (a, an, the, null). The first system, a menu-based task, mimics cloze activities found in many ESL textbooks. The second, a controlled-editing task, gives students practice with both detecting errors and producing the correct response. Resul...

Individuals with dyslexia show deficits in phonological abilities, rapid automatized naming, short-term/working memory, processing speed, and some aspects of sensory visual processing. There is currently one report the literature that individuals also impairments linguistic prediction. The current study sought to investigate prediction language dyslexia. Forty-one adults 43 typically-developing...

Amazon’s Mechanical Turk service makes linguistic experimentation quick, easy, and inexpensive. However, researchers have not been certain about its reliability. In a series of experiments, this paper compares data collected via Mechanical Turk to those obtained using more traditional methods One set of experiments measured the predictability of words in sentences using the Cloze sentence compl...

This event-related potential study examined the impact of imitating an unfamiliar accent on the processing of spoken words embedded in sentential contexts produced in that accent. The cloze probability effect in two groups of southern French speakers after they had to either listen to or imitate sentences spoken by a Belgian French speaker was tested. Speakers who did not imitate the unfamiliar...

The Story Cloze Test consists of choosing a sentence that best completes a story given two choices. In this paper we present a system that performs this task using a supervised binary classifier on top of a recurrent neural network to predict the probability that a given story ending is correct. The classifier is trained to distinguish correct story endings given in the training data from incor...

Semantic scripts is a conceptual representation which defines how events are organized into higher level activities. Practically all the previous approaches to inducing script knowledge from text relied on count-based techniques (e.g., generative models) and have not attempted to compositionally model events. In this work, we introduce a neural network model which relies on distributed composit...

Scripts represent knowledge of stereotypical event sequences that can aid text understanding. Initial statistical methods have been developed to learn probabilistic scripts from raw text corpora; however, they utilize a very impoverished representation of events, consisting of a verb and one dependent argument. We present a script learning approach that employs events with multiple arguments. U...

Implicit arguments are not syntactically connected to their predicates, and are therefore hard to extract. Previous work has used models with large numbers of features, evaluated on very small datasets. We propose to train models for implicit argument prediction on a simple cloze task, for which data can be generated automatically at scale. This allows us to use a neural model, which draws on n...

Two large-scale cloze-style context-question-answer datasets have been introduced recently: i) the CNN and Daily Mail news data and ii) the Children’s Book Test. Thanks to the size of these datasets, the associated task is well suited for deep-learning techniques that seem to outperform all alternative approaches. We present a new, simple model that is tailor made for such question-answering pr...