Class-Based Order-Independent Models of Natural Language for Bayesian Auto-Complete Inference

Morten Hagen, Piyush Arora, Rahul Ghosh, Dawn Thomas, Salil Rajeev Joshi

Abstract: We introduce a model for auto-complete of general queries via Bayesian inference. To that end, we address three issues: First, the problem of predicting a word given previous words in a text. Usually, the context words are treated as a directional sequence. In our approach, we introduce a set-based class language model with order-independence, modeling the context words as a set of classes. Second, towards the task of predicting the next word’s class based on the classes of previous words plus an incomplete word prefix, we present a Bayesian framework that incorporates the set-based class language model in conjunction with an ontology. Third, regarding the auto-complete problem, we provide complete query suggestions via abstract class-space search which determines similar historical queries that contain the classes of previous words plus the next word’s predicted class. Subsequently, we apply the model to auto-complete inference in a system setting, in which users can access data via natural language queries.