Annals of Computer Science and Information Systems, Volume 17

DOI: http://dx.doi.org/10.15439/2018F297

Citation: Communication Papers of the 2018 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 17, pages 37–42 (2018)

Full text

Abstract. A chat dialogue system, a chatbot, or a conversational agent is a computer program designed to hold a conversation using natural language. Many popular chat dialogue systems are based on handcrafted rules, written in Artificial Intelligence Markup Language (AIML). However, a manual design of rules requires significant efforts, as in practice most chatbots require hundreds if not thousands of rules. This paper presents the method of automated extraction of AIML rules from real Twitter conversation data. Our preliminary experimental results show the possibility of obtaining natural-language conversation between the user and a dialogue system without the necessity of handcrafting its knowledgebase.

References

1. B. AbuShawar and E. Atwell, “ALICE chatbot: trials and outputs,” Computación y Sistemas, vol. 19, no. 4, pp. 625–632, 2015.
2. R. Higashinaka et al, “Towards an open-domain conversational system fully based on natural language processing,” in Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, 2014, pp. 928–939.
3. T. Bickmore and J. Cassell, “Relational agents: a model and implementation of building user trust,” in Proceedings of the SIGCHI conference on Human factors in computing systems, 2001, pp. 396–403.
4. B. A. Shawar and E. Atwell, A comparison between Alice and Elizabeth chatbot systems: University of Leeds, School of Computing research report 2002.19, 2002.
5. H. Yamaguchi and M. Mozgovoy, “Generating AIML Rules from Twitter Conversations,” vol. Communication Papers of the 2017 Federated Conference on Computer Science and Information Systems (FedCSIS), pp. 59–61, 2017.
6. F. Bessho, T. Harada, and Y. Kuniyoshi, “Dialog system using real-time crowdsourcing and twitter large-scale corpus,” in Proceedings of the 13th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2012, pp. 227–231.
7. Twitter Inc, Twitter Streaming API. Available: https://dev.twitter.com/streaming/overview.
8. R. Wallace, “The elements of AIML style,” Alice AI Foundation, 2003.
9. J. Ramos and others, “Using tf-idf to determine word relevance in document queries,” in Proceedings of the first instructional conference on machine learning, 2003, pp. 133–142.
10. T. Kudo, MeCab: Yet Another Part-of-Speech and Morphological Analyzer. Available: https://sourceforge.net/projects/mecab.
11. ALICE A.I. Foundation, Program AB. Available: https://code.google.com/archive/p/program-ab.
12. C. Stratton, PyAIML -- The Python AIML Interpreter. Available: https://github.com/creatorrr/pyAIML.
13. C.-W. Liu et al, “How not to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation,” arXiv preprint https://arxiv.org/abs/1603.08023, 2016.
14. C. Chakrabarti and G. F. Luger, “A Framework for Simulating and Evaluating Artificial Chatter Bot Conversations,” in FLAIRS Conference, 2013.
15. N. M. Radziwill and M. C. Benton, “Evaluating Quality of Chatbots and Intelligent Conversational Agents,” arXiv preprint https://arxiv.org/abs/1704.04579, 2017.
16. A. P. Saygin and I. Cicekli, “Pragmatics in human- computer conversations,” Journal of Pragmatics, vol. 34, no. 3, pp. 227–258, 2002.
17. H. P. Grice, “Logic and conversation,” 1975, pp. 41– 58, 1975.
18. J. L. Austin, “How to Do Things with Words (Cambridge,” Mass: Harvard, vol. 13, 1962.
19. J. R. Searle, Speech acts: An essay in the philosophy of language: Cambridge university press, 1969.
20. G. N. Leech, Principles of pragmatics: Routledge, 2016.