Modeling Semantic Expectation: Using Script Knowledge for Referent Prediction
This work addresses how computational models can better simulate human language prediction, which is incremental and domain-specific to psycholinguistics.
The authors tackled the problem of predicting upcoming discourse referents by comparing models using only linguistic knowledge versus those also incorporating common-sense script knowledge, finding that script knowledge significantly improves model estimates of human predictions, but they did not find evidence for the effect of predictability on referring expression type.
Recent research in psycholinguistics has provided increasing evidence that humans predict upcoming content. Prediction also affects perception and might be a key to robustness in human language processing. In this paper, we investigate the factors that affect human prediction by building a computational model that can predict upcoming discourse referents based on linguistic knowledge alone vs. linguistic knowledge jointly with common-sense knowledge in the form of scripts. We find that script knowledge significantly improves model estimates of human predictions. In a second study, we test the highly controversial hypothesis that predictability influences referring expression type but do not find evidence for such an effect.