Showing papers on "AIML published in 2006"

iAIML: a Mechanism to Treat Intentionality in AIML Chatterbots

Abstract: This paper presents iAIML, a mechanism to treat intentional information based on AIML, a state-of-the-art technology in chatterbot development. Our main goal was to improve dialogues with AIML chatterbots. iAIML adds structure to AIML bases, incorporating intentions and rules used in sentence interpretation and generation. We adopted as linguistic base the Conversational Analysis Theory (CAT), which considers intentionality in adjacent pairs in dialogue, facilitating the establishment of consistent dialogues between chatterbots and users. Tests with the implemented solution showed feasibility of the proposed approach. This is an original work with several contributions, such as the innovative and effective use of CAT, and a consistent modular structure of the iAIML base, favoring reuse and maintenance.

Using instant messaging to provide an intelligent learning environment

Abstract: Instant Messaging enables learners and educators to interact in an on-line environment. In this paper, we propose an intelligent ChatBot system, based on instant messaging, for student on-line coaching in an English learning environment. The proposed ChatBot facilitates synchronous communication with students by using ready reference materials including, dictionaries, authorized conversation material with speaking, and a question-answering function. The agent records and analyzes conversations so that the teacher can assess students' progress. Our contribution in this paper is that we integrate the NLP Tool and AIML into an instant messaging-based ChatBot for English as a Second Language programs.

Endowing a Virtual Character with Personalization Capabilities

Abstract: This paper describes a virtual character placed in an educational environment with the purpose of motivating and involving students in the activities proposed. The character can communicate with users in natural-language; it can learn students' profiles and use this knowledge to recommend appropriate contents and activities. Three main elements compose the character's architecture: an AIML-based mechanism, which endows the character with its communication abilities; a profile management system, which collects and organizes students information; and a recommender system, which uses the student's profiles and behavioral patterns to make content recommendations. The character was placed in an educational environment and used in an experiment with 53 computer science students. The results of the experiment are presented here, as well as conclusions and directions for future work

AIML (Artificial Intelligence Markup Language) for Online Chinese Language Learning Assessment.

Abstract: Are there relationships between Chinese language learners' asked questions while they are talking with a virtual robot and their Chinese language proficiency as well as other relevant information such as their psychology, their self-confidence, their interested complementary, supplementary information etc.? How to use them to correctly detect learners' language proficiency and all related information if the relationships do exist? The thesis is going to identify these relationships; test these relationships; find the causation of these relationships; explore the implementation of using these relationships. The researcher used a hybrid of quantitative, qualitative, case study and classical 'positivistic' design with which 30 Chinese language learners were selected as micro cases and the relationships between their asked questions while talking with a virtual robot and their Chinese proficiency as well as their psychology, their self-confidence, their interested complementary, supplementary information etc are identified, tested, their implementation explored. So we may use Chinese language learner's asked questions while they have a free conversation with a virtual robot to correctly detect their Chinese proficiency level, their psychology, their self-confidence, their interested complementary, supplementary information etc. according to the test of the researcher's sample statistics. This is efficient, because learners asked questions are the questions they really want to know from their free will without extra time required for a formal survey and assessment.

A man-machine interaction software-robot for E-commerce order human-like real-time processing

Abstract: According to the difficulties in real-time online negotiation between buyers and sellers during the order processing under E-commerce, the work flow,the structure,and the knowledge-processing flow of man-machine interaction software-robot and inference mechanism have been designed by adopting the working mechanism of ALICE.Applying the technology of JAVA,Program D and AIML and utilizing database technology,knowledge engineering,inference rules and inference strategy,a man-machine interaction software-robot with order real-time processing has been realized.It is beneficial for this research to widen the applications of ALICE,and provide a new way for real-time online negotiation in E-commerce orders.