Development of a stochastic dialog m
نویسندگان
چکیده
We present an approach for the development of a dialog manager based on stochastic models for the representation of the dialogue structure and strategy. This dialog manager processes semantic representations and, when it is integrated with our understanding and answer generation modules, it performs natural language dialogs. It has been applied to a Spanish dialogue system which answers telephone queries about train timetables.
منابع مشابه
A stochastic approach for dialog management based on neural networks
In this article, we present an approach for the construction of a stochastic dialog manager, in which the system answer is selected by means of a classification procedure. In particular, we use neural networks for the implementation of this classification process, which takes into account the data supplied by the user and the last system turn. The stochastic model is automatically learnt from t...
متن کاملAn Investigation into the Relationship between Dialog and Narrative Elements of the Holy Quran from a Literary Perspective
After more than 14 centuries, the expressive inimitability of the holy Quran opens new dimensions for thinkers every day. One of these angles is the study of the story and its relation to the element of dialog. The purpose of this article is to look into this issue in the verses of the holy Quran. For this purpose, the methods and techniques of storytelling in the Quran, the characteristics of ...
متن کاملA Collaborative Stochastic Closed-loop Supply Chain Network Design for Tire Industry
Recent papers in the concept of Supply Chain Network Design (SCND) have seen a rapid development in applying the stochastic models to get closer to real-world applications. Regaring the special characteristics of each product, the stracture of SCND varies. In tire industry, the recycling and remanufacturing of scraped tires lead to design a closed-loop supply chain. This paper proposes a two-st...
متن کاملLearning of stochastic d through a dialog simulati
We present an approach for the learning of stochastic dialog models using a technique of automatic generation of dialogs. We have applied it to achieve a better performance in our dialog system, which answers telephone queries about train timetables in Spanish. Besides interacting with real users, the stochastic dialog manager can now interact with other module, in the role of the user, develop...
متن کاملMon .P1d .01 13:30–15:30 Portability of Semantic Annotations for Fast Development of Dialogue Corpora
This paper presents a new approach for dynamically increasing the coverage of a Statistical Dialog Manager. A Stochastic Finite-State Transducer for dialog management is estimated using a dialog simulator. This corpusbased model can cover most typical user behavior; however, sometimes unexpected situations may arise. Whenever these situations occur, the Dialog Manager model has no information t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2003