Background: The statistical modeling of biomedical corpora could yield integrated, coarse-to-fine views of biological phenomena that complement discoveries made from analysis of m...
David M. Blei, K. Franks, Michael I. Jordan, I. Sa...
Popular image retrieval schemes generally rely only on a single mode, (either low level visual features or embedded text) for searching in multimedia databases. Many popular image...
Representing documents by vectors that are independent of language enhances machine translation and multilingual text categorization. We use discriminative training to create a pr...
The paper presents a semi-automated technique for feature location in source code. The technique is based on combining information from two different sources: an execution trace, ...
The paper addresses language model adaptation for automatic lecture transcription by fully exploiting presentation slide information used in the lecture. As the text in the presen...