An ultimate goal of AI is to build end-to-end systems that interpret natural language, reason over the resulting logical forms, and perform actions based on that reasoning. This r...
Bag-of-words approaches to information retrieval (IR) are effective but assume independence between words. The Hyperspace Analogue to Language (HAL) is a cognitively motivated and...
The current architecture for the Semantic Web, with its emphasis on RDF syntactic and semantic compatability, has severe problems when expressive Semantic Web languages are incorpo...
This paper presents a direct word reordering model with novel syntax-based features for statistical machine translation. Reordering models address the problem of reordering source...
Tree based translation models are a compelling means of integrating linguistic information into machine translation. Syntax can inform lexical selection and reordering choices and...