Probabilistic Modeling of Discourse-aware Sentence Processing

Probabilistic models of sentence comprehension are increasingly relevant to ques-tions concerning human language processing. However, such models are often limited to syntactic factors. This restriction is unrealistic in light of experimental results suggesting interactions between syntax and other forms of linguistic infor-mation in human sentence processing. To address this limitation, this paper intro-duces two sentence processing models which augment a syntactic component with information about discourse co-reference. The novel combination of probabilistic syntactic components with co-reference classifiers permits them to more closely mimic human behavior than existing models. The first model uses a deep model of linguistics, based in part on probabilistic logic, allowing it to make qualitative pre-dictions on experimental data; the second model uses shallow processing to make quantitative predictions on a broad-coverage reading-time corpus. 1