We propose a new discriminative framework, namely Hidden Dynamic Conditional Random Fields (HDCRFs), for building probabilistic models which can capture both internal and external...
The difference between using one mobile phone and another can feel like learning a new language based on our extensive experience designing mobile applications for spatial data na...
Recurrent neural networks are able to store information about previous as well as current inputs. This "memory" allows them to solve temporal problems such as language r...
Statistical topic models provide a general data-driven framework for automated discovery of high-level knowledge from large collections of text documents. While topic models can p...
Chaitanya Chemudugunta, Padhraic Smyth, Mark Steyv...
Document understanding techniques such as document clustering and multi-document summarization have been receiving much attention in recent years. Current document clustering meth...
Dingding Wang, Shenghuo Zhu, Tao Li, Yun Chi, Yiho...