WordNet: a lexical database for English
Communications of the ACM
ELIZA—a computer program for the study of natural language communication between man and machine
Communications of the ACM
Measurement and evaluation of embodied conversational agents
Embodied conversational agents
An Approach for Measuring Semantic Similarity between Words Using Multiple Information Sources
IEEE Transactions on Knowledge and Data Engineering
PARADISE: a framework for evaluating spoken dialogue agents
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
The blind men and the elephant revisited
From brows to trust
Embodied conversational agents on a common ground
From brows to trust
Empirical evaluation methodology for embodied conversational agents
From brows to trust
Sentence Similarity Based on Semantic Nets and Corpus Statistics
IEEE Transactions on Knowledge and Data Engineering
Applied Intelligence
Natural language scripting within conversational agent design
Applied Intelligence
Hi-index | 0.00 |
This paper presents a novel framework for constructing a Semantic-Based Conversational Agent (SCAF). Traditional conversational agents (CA) interpret scripts using structural patterns of sentences, which require the script writer to consider every possible permutation that a user may send as input to the CA. This is a time-consuming process, which takes no consideration of semantic content, working solely with the structural form of the sentence. Furthermore, this has proven to be a high maintenance task that can produce some unforeseen consequences when modifying or introducing new patterns into a script. This invariably results in the script writer reassessing the entire script to prevent such occurrences. Different script writers possess differing levels of skill and as such this can prove to be an exasperating task. The proposed SCAF interprets scripts consisting of natural language sentences by means of a semantic sentence similarity measure. User input is measured semantically against the natural language sentences of the context in order to respond with an appropriate output. Such scripting is effortless and alleviates the burden of the traditional pattern-scripted methodologies. Evaluation of the framework has highlighted its potential and shown improvements on traditional CAs.