Dialog Systems based on Markov decision processes over two real tasks

In this work the state of the art of the automatic dialogue strategy management using Markov decision processes (MDP) with reinforcement learning (RL) is described. Partially observable Markov decision processes (POMDP) are also described. To test the validity of these methods, two spoken dialogue systems have been developed. The first one is a spoken dialogue system for weather forecast providing, and the second one is a more complex system for train information. With the first system, comparisons between a rule-based system and an automatically trained system have been done, using a real corpus to train the automatic strategy. In the second system, the scalability of these methods when used in larger systems has been tested.

The Vietnamese shrimp trade: livelihoods analysis of stakeholders and market chain analysis

Aquaculture and capture fisheries in Vietnam have been increasing fast in the last decade, especially aquaculture growth rate is 12% for the 1999 – 2003 period, contributing a significant part into the hunger eradication and poverty reduction1. Vietnam is to be ranked into one of the countries potential to produce the aquatic economic in the world, and the fact is that, after 40 years of establishing, the fisheries sector has made remarkable contributions to the country. By the list, at the moment the aquatic products make up about 4 - 5% of GDP and create job opportunities for over 3 three million employees (VASEP, 2004), in which the largest contribution is from shrimp farming. [PDF contains 124 pages.]