JaTeDigo is a natural language interface (in Portuguese) to a cinema database that has to deal with a vocabulary of more than 2500000 movies, actors and staff names. As our tools were not able to deal with such a huge amount of information, we decided to profit from full-text queries to the database to support named entity recognition (NER) and syntactic analysis of questions. This paper describes this methodology and evaluates it within JaTeDigo.
展开▼