Abstract
This paper presents a novel Semantic-Based Conversational Agent (SCA). Traditional conversational agents (CA) interpret scripts consisting of structural patterns of sentences, which take no consideration of semantic content. The script writer must therefore anticipate the many variations of input the user may respond with during dialogue. This is evidently a high maintenance task. Furthermore, different script writers possess differing levels of skill and as such this can prove to be an exasperating task. The proposed SCA 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 current context in order to respond with an appropriate output string. Such scripting is effortless and alleviates the burden of the traditional pattern-scripted languages. Experiments have involved the use of script writers to demonstrate the use of the language. Results have highlighted the potential of the language and shown improvements on traditional pattern-scripted languages.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Michie D (2001) Return of the imitation game. Electron Trans Artif Intell 6(2):203–221
Massaro DW, Cohen MM, Beskow WJ, Cole RA (1998) Developing and evaluating conversational agents. University of California, Santa Cruz
Cassell J (2000) Embodied conversational agents. MIT Press, Cambridge
Sanders GA, Scholtz J (2000) Measurement and evaluation of embodied conversational agents. In: Cassell J, Sullivan J, Prevost S, Churchill E (eds) Embodied conversational agents. MIT Press, Cambridge
Isbister K, Doyle P (2004) The blind men and the elephant revisited: evaluating interdisciplinary embodied conversational agents. In: Ruttkay Z, Pelachaud C (eds) From brows to trust. Kluwer Academic, Norwell, pp 3–26. Chapter 1
Malatesta L, Raouzalou A, Karpouzis K, Kollias S (2009) Towards modeling embodied conversational agent character profiles using appraisal theory predictions in expression synthesis. Appl Intell 30(1):58–64
Weizenbaum J (1966) ELIZA—a computer program for the study of natural language communication between man and machine. Commun ACM 9:36–45
O’Shea K, Bandar Z, Crockett K (2008) A novel approach for constructing conversational agents using sentence similarity measures. In: World Congress on engineering, international conference on data mining and knowledge engineering, London, pp 321–1149
O’Shea K, Bandar Z, Crockett K (2009) A semantic-based conversational agent framework. In: The 4th international conference for Internet technology and secured transactions (ICITST-2009), London, 9–12 November 2009, pp 92–99. Technical Co-Sponsored by IEEE UK/RI Communications Chapter
O’Shea K, Bandar Z, Crockett K (2010) Application of a semantic-based conversational agent to student debt management. In: World Congress on computational intelligence, IEEE international conference on fuzzy systems, Barcelona, July 2010, pp 760–766
O’Shea K, Bandar Z, Crockett K (2010) A proposed mechanism to memory simulation within a semantic-based conversational agent framework. In: IEEE international conference on systems, man, and cybernetics, Istanbul, October 2010
O’Shea K, Bandar Z, Crockett K (2009) Towards a new generation of conversational agents using sentence similarity. In: Ao S-L, Gelman L (eds) Advances in electrical engineering and computational science. Lecture notes in electrical engineering, vol 39. Springer, Berlin, pp 505–514
O’Shea K, Bandar Z, Crockett K (2011) A conversational agent framework using semantic analysis. Int J Intell Comput Res 1(1):23–32. ISSN 2042 4655
Colby K (1975) Artificial paranoia: a computer simulation of paranoid process. Pergamon, New York. Cited by Mauldin ML (1994) Chatterbots, Tinymuds, and the Turing test: entering the Loebner prize competition. Carnegie Mellon University, Pittsburgh
Carpenter R (2006) Jabberwacky. http://jabberwacky.com. Accessed 14 Apr 2011
Chatbots (2009) http://chatbots.org/chatbot/freudbot. Accessed 13 Mar 2011
ejTalk (2009) http://ejTalk.com. Accessed 13 Mar 2011
Chatbots (2010) http://chatbots.org/chatbot/suzette. Accessed 13 Mar 2011
Wallace R (2003) The elements of AIML style. ALICE Artificial Intelligence Foundations. Cited by Schmaker RP and Chen H (2008) Interaction analysis of the ALICE Chatterbot: a two-study investigation of dialog and domain questioning. University of Arizona
Convagent (2001) InfoBot scripter’s manual. www.convagent.com. Accessed 14 Mar 2011
Landauer TK, Foltz PW, Laham D (1998) Introduction to latent semantic analysis. Discourse Process 25(2–3):259–284
O’Shea K (2012) An approach to conversational agent design using semantic sentence similarity. Appl Intell 37(4):558–568
Li Y, McLean D, Bandar Z, O’Shea JD, Crockett K (2006) Sentence similarity based on semantic nets and corpus statistics. IEEE Trans Knowl Data Eng 18(8):1138–1149
Sammut C (2001) Managing context in a conversational agent. Comput Inf Sci 3(7). 10.1109/wI-IATW.2006.105
Li Y, Bandar ZA, McLean D (2003) An approach for measuring semantic similarity between words using multiple information sources. IEEE Trans Knowl Data Eng 15(4):871–881
Miller GA (1995) WordNet: a lexical database for English. Commun ACM 38(11):39–41
Brown Corpus Information (2005) http://www.clwww.essex.ac.uk/w3s/corpus_ling/content/corpora/list/private/brown/brown.htm. Accessed 01 Apr 2011
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
O’Shea, K. Natural language scripting within conversational agent design. Appl Intell 40, 189–197 (2014). https://doi.org/10.1007/s10489-012-0408-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-012-0408-2