Sciweavers

986 search results - page 77 / 198
» Zero-data Learning of New Tasks
Sort
View
ICPR
2008
IEEE
15 years 11 months ago
Incremental machine learning techniques for document layout understanding
In real-world Digital Libraries, Artificial Intelligence techniques are essential for tackling the automatic document processing task with sufficient flexibility. The great variab...
Floriana Esposito, Marenglen Biba, Stefano Ferilli...
NAACL
2007
14 years 11 months ago
Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System
This paper investigates the problem of bootstrapping a statistical dialogue manager without access to training data and proposes a new probabilistic agenda-based method for simula...
Jost Schatzmann, Blaise Thomson, Karl Weilhammer, ...
NIPS
1993
14 years 11 months ago
Credit Assignment through Time: Alternatives to Backpropagation
Learning to recognize or predict sequences using long-term context has many applications. However, practical and theoretical problems are found in training recurrent neural networ...
Yoshua Bengio, Paolo Frasconi
NAACL
2010
14 years 7 months ago
Unsupervised Modeling of Twitter Conversations
We propose the first unsupervised approach to the problem of modeling dialogue acts in an open domain. Trained on a corpus of noisy Twitter conversations, our method discovers dia...
Alan Ritter, Colin Cherry, Bill Dolan
WWW
2008
ACM
15 years 10 months ago
Learning to rank relational objects and its application to web search
Learning to rank is a new statistical learning technology on creating a ranking model for sorting objects. The technology has been successfully applied to web search, and is becom...
Tao Qin, Tie-Yan Liu, Xu-Dong Zhang, De-Sheng Wang...