Advances in Engineering Advances in Engineering features breaking research judged by Advances in Engineering advisory team to be of key importance in the Engineering field. Papers are selected from over 10,000 published each week from most peer reviewed journals.
Significance Statement
Chatter bots are software programs that engage in simulated conversations through a text-based input medium. Many businesses have automated their online customer service support by deploying chatter bots. These customer service chatter bots interact with customers, answer their queries, and address service related issues.
Traditional chatter bots perform best in conversations consisting of pairs of utterance exchanges such as question-answer sessions, where the context may or may not switch with every exchange pair. They perform poorly in longer conversations, where the context is maintained over several pairs of utterance exchanges. Existing approaches to conversation generation focus on linguistic and grammatical modeling using natural language processing and computational linguistics techniques to generate individual sentence-level utterances.
Artificial conversation research aims to go beyond individual sentence-level interactions to model the higher level conversation process. A conversation is a process that adheres to well-defined semantic conventions and is contextually grounded in domain-specific knowledge. A modular, robust, and scalable architecture is presented, that combines content semantics and pragmatic semantics to generate higher quality artificial conversations in the customer service domain. The conversational process is modeled using stochastic finite state machines, where the parameters of the model are learned from a corpus of human conversations. Relevant evaluation metrics are also defined for general purpose and domain-specific conversations.
Journal Reference
Expert Systems with Applications, Volume 42, Issue 20, 2015, Pages 6878-6897.
Chayan Chakrabarti, George F. Luger
Computer Science Department MSC01 1130, 1 University of New Mexico, Albuquerque, NM 87131, USA
Abstract
Chatter bots are software programs that engage in artificial conversations through a text-based input medium. They are extensively deployed in customer service applications. Existing approaches to artificial conversation generation emphasize grammatical and linguistic modeling techniques. They focus on generation of discrete sentence-level utterances. These approaches perform poorly in conversational situations requiring contextual continuity over a series of utterances. We present an approach that combines pragmatics with content semantics to generate artificial conversations in the customer service domain. A conversation is a process that adheres to well-defined semantic conventions and is contextually grounded in domain-specific knowledge. We model this using stochastic finite state machines, where the parameters of the model are learned from a corpus of human conversations. We present a specific set of criteria which we then use to evaluate the quality of artificial conversations in the customer service domain. We also compare chatter bot generated artificial conversations with human generated natural conversations in this domain.
Go To Expert Systems with Applications
