This paper presents a recognition system for isolated handwritten Bangla words, with a fixed lexicon, using a left-right Hidden Markov Model (HMM). A stochastic search method, nam...
Early question and answering (QA) systems focused on keyword search among documents for answers. However, such systems can only answer fact-based questions. It becomes clear that ...
This paper presents an efficient indexing and retrieval scheme for searching in document image databases. In many non-European languages, optical character recognizers are not very...
How does a search engine company decide what ads to display with each query so as to maximize its revenue? This turns out to be a generalization of the online bipartite matching p...
Aranyak Mehta, Amin Saberi, Umesh V. Vazirani, Vij...
Statistical models of word-sense disambiguation are often based on a small number of contextual features or on a model that is assumed to characterize the interactions among a set...