Abstract

We study the influence of context on sentence acceptability. First we compare the crowd source acceptability ratings of sentences judged in isolation, with a relevant context, and with an irrelevant context. Our results show that context induces a cognitive load for humans, which compresses the distribution of ratings. Moreover, in relevant contexts we observe a discourse coherence effect which uniformly raises acceptability. We then test unidirectional and bidirectional neural language models for their ability to predict acceptability ratings. The bidirectional models give very promising results, with the best model achieving a new state-of-the-art for unsupervised acceptability prediction. The two sets of experiments provide insights into the cognitive aspects of sentence processing, and central issues in the computational modelling of text and discourse. (Joint work with Jey Han Lau, The University of Melbourne; Carlos Armendariz, Queen Mary University of London; Matthew Purver, Queen Mary University of London; and Chang Shu,University of Nottingham Ningbo China)