Determining the similarity of short text snippets, such as search queries, works poorly with traditional document similarity measures (e.g., cosine), since there are often few, if...
The majority of people in rural developing regions do not have access to the World Wide Web. Traditional network connectivity technologies have proven to be prohibitively expensiv...
Jay Chen, Lakshminarayanan Subramanian, Jinyang Li
MAX is a system that facilitates human-centric search of the physical world. It allows humans to search for and locate objects as and when they need it instead of organizing them ...
Spoken language interfaces based on interactive semantic language models [16, 14] allow probabilities for hypothesized words to be conditioned on the semantic interpretation of th...
Lane Schwartz, Luan Nguyen, Andrew Exley, William ...
This paper presents a lightweight method for unsupervised extraction of paraphrases from arbitrary textual Web documents. The method differs from previous approaches to paraphrase...