Computer science as a discipline is failing to reach a diverse audience. As a result, computational illiteracy threatens many groups of underserved students—women, minorities an...
Grammatical relationships are an important level of natural language processing. We present a trainable approach to find these relationships through transformation sequences and-e...
We present a machine learning approach for the task of ranking previously answered questions in a question repository with respect to their relevance to a new, unanswered referenc...
Abstract. We consider the problem of learning stochastic tree languages, i.e. probability distributions over a set of trees T(F), from a sample of trees independently drawn accordi...
This paper presents a method for learning a semantic parser from ambiguous supervision. Training data consists of natural language sentences annotated with multiple potential mean...