Over the past two years Exetel have sponsored a formal program to develop such an AI system at SLIIT by funding a professorship and PhD program.
The conference runs from 16 to 19 August. The full paper will subsequently be published at IEEEXplore with the conference proceedings.Automated Question Answering for Customer Helpdesk Applications
Lahiru Samarakoon
Faculty of Engineering
University of Moratuwa
Sri Lanka
Sisil Kumarawadu
Faculty of Engineering
University of Moratuwa
Sri Lanka
Abstract—This paper describes a closed domain question answering system which can be used as the first step in automating
a customer help desk of a commercial organization. Even though there has been an increasing interest in data-driven methods
over the past decade to achieve more natural human-machine interactions, such methods require a large amount of manually
labeled representative data on how users converse with a machine. However, this is a strong requirement that is difficult to be satisfied
in the early phase of system development. The knowledge based approach that we present here is aimed at maximally
making use of the user experience available with the customer services representatives (CSRs) in the organization and hence not
relying on application data.
The approach takes into account the syntactic, lexical, and morphological variations, as well as a way
of synonym transduction that is allowed to vary over the systems knowledge base. The query understanding method, which is based
on a ranking algorithm and a pattern writing process, takes into account the intent, context, and content components of natural
language meaning, as well as the word order. A genetic algorithm based method is presented for regularly updating the ranking
parameters to adapt to changes in the nature of users’ queries over time. We present an evaluation of our system deployed in
a real-world enterprise help desk environment.