Content uploaded by Huma Shah
Author content
All content in this area was uploaded by Huma Shah
Content may be subject to copyright.
A preview of the PDF is not available
Constraining Random Dialogue in Modern Eliza
Abstract and Figures
One of the differences between natural conversational entities – NCE (humans) and artificial conversational entities – ACE (such as Carpenter’s Jabberwacky), is the ability the former have to constrain random output during dialogue. When humans want to participate in, and pursue conversation with each other they maintain coherent dialogue through contextual relevance, create metaphors – fusing seemingly unrelated ideas to ensure abstract points are understood, and indicate topic change at mutually acceptable junctures.
Figures - uploaded by Huma Shah
Author content
All figure content in this area was uploaded by Huma Shah
Content may be subject to copyright.
... It is a straightforward system based on simple, non-personalized pattern-matching answers. Currently, some implementations of Eliza are still available online [16], but the lack of up-to-date functionalities leave it as a simple research prototype. ...
... In order to make the medical dictionary easier to consult, the knowledge base has been further extended by mapping the above mentioned diseases and symptoms with those of the 'Italian Consumer-oriented Medical Vocabulary' (ICMV). 16 The ICMV vocabulary acts as a link between medical language and the language used by patients, and aims to provide commonly used descriptions of terms related to medical terminology. 169 of the most common diseases and 236 symptoms have been manually mapped. ...
In this article, we present HealthAssistantBot, an intelligent virtual assistant able to talk with patients in order to understand their symptomatology, suggest doctors, and monitor treatments and health parameters. In a simple way, by exploiting a natural language-based interaction, the system allows the user to create her health profile, to describe her symptoms, to search for doctors or to simply remember a treatment to follow. Specifically, our methodology exploits machine learning techniques to process users symptoms and to automatically infer her diseases. Next, the information obtained is used by our recommendation algorithm to identify the nearest doctor who can best treat the user’s condition, considering the community data. In the experimental session we evaluated our HealthAssistantBot with both an offline and online evaluation. In the first case, we assessed the performance of our internal components, while in the second one we carried out a study involving 102 subjects who interacted with the conversational agent in a daily use scenario. Results are encouraging and showed the effectiveness of the strategy in supporting the patients in taking care of their health.
In this paper, we look at a specific issue with practical Turing tests, namely the right of the machine to remain silent during interrogation. In particular, we consider the possibility of a machine passing the Turing test simply by not saying anything. We include a number of transcripts from practical Turing tests in which silence has actually occurred on the part of a hidden entity. Each of the transcripts considered here resulted in a judge being unable to make the ‘right identification’, i.e., they could not say for certain which hidden entity was the machine.
One way to organize an introduction to a handbook is to divide it into the past, present, and future. This is precisely the approach we have adopted. We start with a short history that documents how the field of discourse processes emerged. Next we describe the current trends in investigating discourse processes. We end with our forecast of how the field is destined to evolve into the future or how we hope it will evolve. The purpose of this introduction is to set the stage for the subsequent chapters rather than to provide a comprehensive overview of the field.
The geography of a modern Eliza provides an illusion of natural language understanding, through sophisticated techniques capturing context and interaction-based learning. This can be seen in the best of the hundred-plus programmes entered into Chatterbox Challenge 2005 (CBC 2005), an alternative to Loebner’s Contest for artificial intelligence, Turing’s measure for intelligence through conversation. These artificial conversational entities (ACE) are able to maintain lengthy textual dialogues. This paper presents the experience of the author as one of the Judges in CBC 2005. Not ‘bathed in language experience’ like their human counterparts, Eliza’s descendants respond at times humorously and with knowledge but they lack metaphor use, the very feature of everyday human discourse. However, ACE find success as virtual e-assistants in single topic domains. Swedish furniture company IKEA deploys animated avatar Anna, a virtual customer service agent in twenty thousand conversations daily across eight country sites in six languages, including English. Anna provides IKEA’s customers with an alternative and more natural query system, than key-word only search, to find products and prices. The author’s findings show that modern Eliza’s appear to have come a long way from their ancestor but understanding remains in the head of the human user. Until metaphor design is included ACE will remain machine-like
Psychologism and Behaviorism Psychological Review
- N Block
Block, N. (1981) Psychologism and Behaviorism Psychological Review, LXXXX, No. 1, January 5-
43.
A Psychological Model of Grounding and Repair in Dialog) from The Chatterbox Challenge – (selecting Jabberwacky) http://www.chatterboxchallenge.com/ date visited
- J Cahn
- E Brennan
Cahn, J,E. and Brennan, S.E. (1999) A Psychological Model of Grounding and Repair in Dialog,
Proceedings, AAAI, Fall symposium on Psychological Models of Communication in
Collaborative Systems (pp 25-33), North Falmouth, MA: American Association for Artificial
Intelligence
Carpenter, R. (2005) from The Chatterbox Challenge – (selecting Jabberwacky)
http://www.chatterboxchallenge.com/ date visited: May 2 nd, 2005; time: 19.19 and
http://www.jabberwacky.com various dates visited including November 18 th 2005
The Chatterbox Challenge http://www.chatterboxchallenge.com date visited: November 16 th
CBC (2005) The Chatterbox Challenge
http://www.chatterboxchallenge.com date visited: November 16 th 2005; time: 15.43
Spoken word production: a theory of lexical access, Special series of inaugural articles by members of National Academy of Sciences
- W J Levelt
Levelt, W.J.M (2001) Spoken word production: a theory of lexical access, Special series of inaugural
articles by members of National Academy of Sciences, The Netherlands.
Loebner Prize 2005 Contest Transcripts http://loebner.net/Prizef
- H Loebner
Loebner, H. (2005) Loebner Prize 2005 Contest Transcripts
http://loebner.net/Prizef/2005_Contest/Transcripts.html dates visited: September 19th, September
23 rd ; October 1st 2005
Alice: an ACE in Digitaland
- H Shah
Shah, H. (2005) Alice: an ACE in Digitaland. Triple C: Journal of Cognition, Communication and
Co-operation, forthcoming special edition Proceedings of European Conference on Computing
and Philosophy (ECAP 2005)