We propose new methods to exploit contemporaneous text, such as on-line news articles, to improve language models for automatic speech recognition and other natural language proce...
At Hewlett-Packard Laboratories we want to know how inexpensive it can be to endow mobile personal assistants with the ability to speak naturally with their users. To this end, we ...
In this paper we tackle the problem of document image retrieval by combining a similarity measure between documents and the probability that a given document belongs to a certain ...
Albert Gordo, Jaume Gibert, Ernest Valveny, Mar&cc...
combinFormation is a tool that enables browsing and collecting information elements in a generative space. By generative, we mean that the tool is an agent that automatically retr...
Andruid Kerne, Vikram Sundaram, Jin Wang, Madhur K...
As multimedia becomes an integral part of collaborative systems, we must understand how to design such systems to support users’ rich set of existing interaction skills, rather ...