Modelization and experimentation of conversational policies for non task oriented agents based on dissonance and relevance theories
نویسندگان
چکیده
We propose a model for dialogue between non task oriented agents, based on the dissonance and relevance theories. Non task oriented agents are studied as a model for non expert agents, as opposed to task oriented agents, in order to provide models for social science simulations. Dialogue between non task oriented agents can not be modelled like task oriented dialogue because no criterium is provided to define the beginning and the termination of a dialogue, with respect to a common goal. The dissonance theory has been proposed by cognitive researchers as a drive for acting. Therefore, dissonance is a seducing theory to model the motivation of an agent to open a dialogue. Relevance theory is also introduced to model the development and termination phases of such a dialogue. An implemented system in then presented and evaluated.
منابع مشابه
Exploring the Translator\'s Solutions to the Translation of Conversational Implicatures from English into Persian: the Case of Tolkien\'s the Lord of the Rings
The present study aimed to examine the translatorchr('39')s solutions to the translation of conversational implicatures from English into Persian. To do so, 120 conversational implicatures were extracted from the novel the Lord of the Rings (Tolkien, 1954) and classified based on Gricechr('39')s (1975) categorization of Maxims, including quality, quantity, relevance, and manner. Mur Duenaschr('...
متن کاملThe Effect of Task Type and Task Orientation on L2 Vocabulary Learning
This study was conducted to investigate the effect of meaning-focused versus form-focused input-oriented and output-oriented task-based instruction on elementary level Iranian EFL Learners’ vocabulary comprehension and recall. For this purpose, a sample of 120 male students from a private school in Tehran was selected through convenience sampling and based on availability. The participants were...
متن کاملStrategy and Policy Learning for Non-Task-Oriented Conversational Systems
We propose a set of generic conversational strategies to handle possible system breakdowns in non-task-oriented dialog systems. We also design policies to select these strategies according to dialog context. We combine expert knowledge and the statistical findings derived from data in designing these policies. The policy learned via reinforcement learning outperforms the random selection policy...
متن کاملAudience awareness of Persian learners of English writing: Towards a model of task-oriented strategies
Persian learners of English often avoid attending to audience considerations, which brings them lower scores. The present study was conducted in a major university in Iran to help Persian learners develop a sense of audience awareness in writing. Thirty five Persian students of English were trained with a focus on process-oriented instruction. The intended task was a...
متن کاملIncorporating Cognitive Linguistic Insights into Classrooms: the Case of Iranian Learners’ Acquisition of If-Clauses
Cognitive linguistics gives the most inclusive, consistent description of how language is organized, used and learned to date. Cognitive linguistics contains a great number of concepts that are useful to second language learners. If-clauses in English, on the other hand, remain intriguing for foreign language learners to struggle with, due to their intrinsic intricacies. EFL grammar books are ...
متن کامل