A General Evaluation Framework for Text Based Conversational Agent

Abstract

This paper details the development of a new evaluation framework for a text based Conversational Agent (CA). A CA is an intelligent system that handle spoken or/and text based conversations between machine and human. Generally, the lack of evaluation frameworks for CAs effects its development. The idea behind any system’s evaluation is to make sure about the system’s functionalities and to continue development on it. A specific CA has been chosen to test the proposed framework on it; namely ArabChat. The ArabChat is a rule based CA and uses pattern matching technique to handle user’s Arabic text based conversations. The proposed and developed evaluation framework in this paper is natural language independent. The proposed framework is based on the exchange of specific information between ArabChat and user called “Information Requirements”. This information are tagged for each rule in the applied domain and should be exist in a user’s utterance (conversation). A real experiment has been done in Applied Science University in Jordan as an information point advisor for their native Arabic students to evaluate the ArabChat and then evaluating the proposed evaluation framework.

Authors and Affiliations

Mohammad Hijjawi, Zuhair Bandar, Keeley Crockett

Keywords

Related Articles

Light but Effective Encryption Technique based on Dynamic Substitution and Effective Masking

Cryptography and cryptanalysis are in ever-lasting struggle. As the encryption techniques advance, the cryptanalysis techniques advance as well. To properly face the great danger of the cryptanalysis techniques, we shoul...

Deep Learning Classification of Biomedical Text using Convolutional Neural Network

In this digital era, the document entries have been increasing days by days, causing a situation where the volume of the document entries in overwhelming. This situation has caused people to encounter with problems such...

Text Mining: Techniques, Applications and Issues

Rapid progress in digital data acquisition tech-niques have led to huge volume of data. More than 80 percent of today’s data is composed of unstructured or semi-structured data. The discovery of appropriate patterns and...

High Lightweight Encryption Standard (HLES) as an Improvement of 512-Bit AES for Secure Multimedia

In today’s scenario, people share information to another people frequently using network. Due to this, more amount of information are so much private but some are less private. Therefore, the attackers or the hackers tak...

Antennas of Circular Waveguides

The design of the circular waveguide antenna is proposed for displacement reflector antennas. For them, we use the frequencies of operation so that our waveguide generates the mode, (Transversal Electric), resulting in a...

Download PDF file
  • EP ID EP106887
  • DOI 10.14569/IJACSA.2016.070304
  • Views 78
  • Downloads 0

How To Cite

Mohammad Hijjawi, Zuhair Bandar, Keeley Crockett (2016). A General Evaluation Framework for Text Based Conversational Agent. International Journal of Advanced Computer Science & Applications, 7(3), 23-33. https://europub.co.uk/articles/-A-106887