Today I uploaded a Flash .swf file to a local server (one I normally use for teaching). The file, based on Jamie Durrant's work, is a chatbot interface that talks to a test bot I have running on the Pandorabots site. It appears to be working quite well with none of the security issues I got when trying to run it from a local machine. Speed is the only problem. Occasionally, the response from the Pandorabot site is a little slow... Maybe I could script a 'filler' output to fill out the wait time if it gets too long.
The URL for the test bot is - Talk to Dick at Pandorabots
Have a play and feel free to add a comment.
Thursday, August 5, 2010
Summer School report
Over the next couple of weeks I'll be going through my notes from the Summer School and adding some posts about the lecture series content.
Suffice to say, at the moment, this was without a doubt the valuable research related experience of my academic career.
Suffice to say, at the moment, this was without a doubt the valuable research related experience of my academic career.
Sunday, July 4, 2010
10th International Summer School and Symposium on Humour and Laughter
University of Zurich
Switzerland
July 5 - 10, 2010
University of Zurich
Switzerland
July 5 - 10, 2010
I've submitted an abstract for the Symposium. Hopefully, it will be accepted. I'd like to test some of the ideas on this audience.
Title: Testing an inversion of Bergson’s ‘new law’ of humour.
Keywords: Artificial intelligence, scriptwriting, agency, humour.
This presentation offers an overview of a PhD project that interrogates of the scriptwriting process as it is applied in a new media, online environment as a confluence of human and non-human agency. The study is underpinned by the theoretical perspectives of humour theory, Actor Network Theory (Callon, Latour, Law et al), the Computers as Social Actors paradigm of Reeves and Nass, and Csikszentmihalyi’s Creativity Theory. The exploration of humour provides the opportunity to explore “what it means to be human by moving back and forth across the [unstable] frontier that separates humanity from animality” and by extension, the frontier between the human and the non-human in general (Critchley, 2002, p.28). Henri Bergson, in his seminal essay on laughter, stated a “new law” of humour, “We laugh every time a person gives us the impression of being a thing” (Bergson 2005, p.28, Original Publication 1911). This project integrates human agency (the scriptwriter and the scriptwriting process) with the nonhuman agency of the artificial intelligence of chatbots (the interface and the scripted processes). As such, it tests if Bergson’s law will stand if it is inverted; will we laugh every time a thing gives the impression of being a person?
- Bergson, H. (2005). Laughter: An essay on the meaning of the comic. Mineola, New York, Dover Publications Inc.
- Callon, M. (1999). Actor-network theory: The market test. In Law, J. & Hassard, J., eds. Actor network theory and after, pp. 181–95. Oxford: Blackwell.
- Critchley, S. (2002). On Humour: Thinking in Action. New York and London, Routledge.
- Csikszentmihalyi, M. (1997). Creativity: flow and the psychology of discovery and invention. New York, Harper Collins.
- Reeves, B. and C. Nass (1996). The Media Equation: how people treat computers, television, and new media like real people and places. New York, Cambridge University Press.
Conference papers etc.
The abstracts below have been accepted for upcoming conferences.
Conference – New Directions in the Humanities - 2010
Title: Humour Theory and Conversational Agents: An application of humour theory in the development of computer-based, conversational agents.
Much of the literature on the development of conversational agents comes from the domain of Human Computer Interaction (HCI) (Buchanan 2008; Cassell et al. 2000; Laurel 1993; Reeves and Nass 1996). The Computers Are Social Actors (CASA) paradigm suggests that a user will respond to a computer-based conversational agent in the same manner they would respond to a real person (Nass, Isbister, and Lee 2000). Shechtman and Horowitz, although critical of the conclusions of the CASA paradigm, suggest there is an “inextricable link between the use of natural language and social interaction. Perhaps relationship behaviors are simply difficult to filter out of communication and may arise as an artefact of using natural language in a conversational situation” (2003, p.288). Whether computers and humans are equal social actors or not may be an unnecessary distinction if the use of natural language is alone sufficient to generate the perception of social interaction and personality. If humour is one of the defining features of ‘human-ness’ then for a computer to truly be a social actor it must be able to engage in novel, surprising and humorous exchanges. This paper surveys a range of humour theories in search of a theory that can be applied to interactions of computer-based conversational agents.
Conference – Arts in Society - 2010
Title: Scripting Humour in Conversational Agents: Improvisation and Emergence of Humorous Interchanges
This paper describes a creative project that will develop a pair of online computer-based conversational agents to interact as ‘comedian’ and ‘straight man’. The project will interrogate the scriptwriting process as it is applied in a new media environment at the confluence of human and non-human agency. In the context of this paper the term ‘scriptwriter’ carries two inter-related definitions: first, as a producer and crafter of dialogue for a character; and second, as a developer of computer script to guide the interactions of the conversational agents. It can be argued that the scriptwriter (in both guises) is part of a larger system of circular causality and is thus embedded within structures that both constrain and enable their actions (Boden 1994, 2004; Bourdieu 1993; Giddens 1979) makes intentional choices to achieve particular aims or outcomes. The interaction of the conversational agents is a result of a creative practice that allows for the emergence of improvised responses based on scripted dialogue choices. This paper will explore the inter-related issues of: scriptwriting; emergence; and, improvisation in a new media environment.
Conference – New Directions in the Humanities - 2010
Title: Humour Theory and Conversational Agents: An application of humour theory in the development of computer-based, conversational agents.
Much of the literature on the development of conversational agents comes from the domain of Human Computer Interaction (HCI) (Buchanan 2008; Cassell et al. 2000; Laurel 1993; Reeves and Nass 1996). The Computers Are Social Actors (CASA) paradigm suggests that a user will respond to a computer-based conversational agent in the same manner they would respond to a real person (Nass, Isbister, and Lee 2000). Shechtman and Horowitz, although critical of the conclusions of the CASA paradigm, suggest there is an “inextricable link between the use of natural language and social interaction. Perhaps relationship behaviors are simply difficult to filter out of communication and may arise as an artefact of using natural language in a conversational situation” (2003, p.288). Whether computers and humans are equal social actors or not may be an unnecessary distinction if the use of natural language is alone sufficient to generate the perception of social interaction and personality. If humour is one of the defining features of ‘human-ness’ then for a computer to truly be a social actor it must be able to engage in novel, surprising and humorous exchanges. This paper surveys a range of humour theories in search of a theory that can be applied to interactions of computer-based conversational agents.
Conference – Arts in Society - 2010
Title: Scripting Humour in Conversational Agents: Improvisation and Emergence of Humorous Interchanges
This paper describes a creative project that will develop a pair of online computer-based conversational agents to interact as ‘comedian’ and ‘straight man’. The project will interrogate the scriptwriting process as it is applied in a new media environment at the confluence of human and non-human agency. In the context of this paper the term ‘scriptwriter’ carries two inter-related definitions: first, as a producer and crafter of dialogue for a character; and second, as a developer of computer script to guide the interactions of the conversational agents. It can be argued that the scriptwriter (in both guises) is part of a larger system of circular causality and is thus embedded within structures that both constrain and enable their actions (Boden 1994, 2004; Bourdieu 1993; Giddens 1979) makes intentional choices to achieve particular aims or outcomes. The interaction of the conversational agents is a result of a creative practice that allows for the emergence of improvised responses based on scripted dialogue choices. This paper will explore the inter-related issues of: scriptwriting; emergence; and, improvisation in a new media environment.
Bot Technology
The implementation of a pair of bots remains problematic. Not for the same reasons as before - those were purely technical. That sort of problem can be addressed with a combination of tenacity, research, expert networking, and cash. Having tried all of these approaches I now have a couple of viable solutions.
The first is to 'employ' the computing research guys at Newcastle to set up the bots on a research server. The only downside to that solution is that I would be need to develop a work method for writing and updating the AIML sets. Being one step removed from owning the server I would need to be get some kind of administrator access - this is not the sort of thing server admin people are very keen on.
The second is to use the 'commercial' site that provides the Pandorabot. I already have a test bot up there and I've found an Flash/Actionscript interface (thanks to Jamie Durrant) that will talk to the Pandorabot server. Cool! This is one comparatively small step away from have two Pandorabot accounts and using the Flash interface to throw output to input from one bot to the other. The advantage of Panadora bot is that I could easily update the AIML and be able to speak to each of the bots individually.
I'll keep playing with the Actionscript to see what I can do.
The first is to 'employ' the computing research guys at Newcastle to set up the bots on a research server. The only downside to that solution is that I would be need to develop a work method for writing and updating the AIML sets. Being one step removed from owning the server I would need to be get some kind of administrator access - this is not the sort of thing server admin people are very keen on.
The second is to use the 'commercial' site that provides the Pandorabot. I already have a test bot up there and I've found an Flash/Actionscript interface (thanks to Jamie Durrant) that will talk to the Pandorabot server. Cool! This is one comparatively small step away from have two Pandorabot accounts and using the Flash interface to throw output to input from one bot to the other. The advantage of Panadora bot is that I could easily update the AIML and be able to speak to each of the bots individually.
I'll keep playing with the Actionscript to see what I can do.
Tuesday, March 30, 2010
Humour Literature and the brick wall...
Through theory we examine practice: in practice we test theory.
My literature review of the domain of humour studies has two broad ambitions.
The link between theory and practice leads to the first ambition of the literature review. The creative work at the core of this research project, the development of humorous conversational agents, needs to be grounded in a theory of humour that can encompass the interaction of human and non-human actors. I feel Bergson's theory supplies this basis. I argue that his “new law” of comedy that states, “We laugh every time a person gives us the impression of being a thing” may be tested by being inverted (Bergson 2005, p.28, Original Publication 1911). That is, will we laugh when a thing gives the impression of being a person? Testing this argument in a creative work is a substantive addition to the field. The logic of undertaking such an inversion test is based on the “Computers as Social Actors” (CASA) paradigm.
Humour has been studied from various perspectives including the psychological, social and anthropological. Each of these domains has contributed a unique theoretical understanding. However, added to these academic understandings of humour are accounts of the practice of humour. For example, Cicero’s De Oratore can be understood as an account of the verbal techniques used to promote a cause or defend a client. Likewise, Stephen Halliwell in the introduction to his translation of Aristotle’s Poetics argues that “The Poetics … represents something in the nature of teaching materials or ‘lecture notes’, produced not as a text for private reading by anyone interested, but for instructional use in an educational context” (Halliwell in Aristotle 1995, p.4). These texts, and more modern ones, provide an insight into the link between theory and practice.
The second ambition is to provide an overview of the existing literature. This overview is structured as a chronology to make explicit the historical order of the threads and concepts that have informed the current state of humour theory.
So far this all sounds 'cool and froody' to use a Zaphod Beeblebrox expression. Truth be told - I'm a lot more like Arthur Dent than the freewheeling Zaphod. I've developed a personal relationship with a brick wall - I keep hitting my head against it and it doesn't seem to mind in the slightest.
My literature review of the domain of humour studies has two broad ambitions.
The link between theory and practice leads to the first ambition of the literature review. The creative work at the core of this research project, the development of humorous conversational agents, needs to be grounded in a theory of humour that can encompass the interaction of human and non-human actors. I feel Bergson's theory supplies this basis. I argue that his “new law” of comedy that states, “We laugh every time a person gives us the impression of being a thing” may be tested by being inverted (Bergson 2005, p.28, Original Publication 1911). That is, will we laugh when a thing gives the impression of being a person? Testing this argument in a creative work is a substantive addition to the field. The logic of undertaking such an inversion test is based on the “Computers as Social Actors” (CASA) paradigm.
Humour has been studied from various perspectives including the psychological, social and anthropological. Each of these domains has contributed a unique theoretical understanding. However, added to these academic understandings of humour are accounts of the practice of humour. For example, Cicero’s De Oratore can be understood as an account of the verbal techniques used to promote a cause or defend a client. Likewise, Stephen Halliwell in the introduction to his translation of Aristotle’s Poetics argues that “The Poetics … represents something in the nature of teaching materials or ‘lecture notes’, produced not as a text for private reading by anyone interested, but for instructional use in an educational context” (Halliwell in Aristotle 1995, p.4). These texts, and more modern ones, provide an insight into the link between theory and practice.
The second ambition is to provide an overview of the existing literature. This overview is structured as a chronology to make explicit the historical order of the threads and concepts that have informed the current state of humour theory.
So far this all sounds 'cool and froody' to use a Zaphod Beeblebrox expression. Truth be told - I'm a lot more like Arthur Dent than the freewheeling Zaphod. I've developed a personal relationship with a brick wall - I keep hitting my head against it and it doesn't seem to mind in the slightest.
More on this later.
Friday, February 19, 2010
GTVH.. additional thoughts
Of late I've been battling with the age old question of authorial intention in relation to the semantic-script theory (or SSTH) of Raskin and the more developed general theory (or GTVH) of Attardo and Raskin.
I've been thinking about my supervisor's work on the structures of political speeches and, in particular, the speeches of Churchill. The semantic and linguistic structures look so much like the structures of humour. Couplets and triplets working, often using incongruous elements, to make a memorable and surprising statement. Maybe this is why they can be so easily parodied? This leads me to question whether the application of the General Theory of Verbal Humour presupposes the intention of the script or performance. Would the GTVH give a 'false positive' if applied to "Now this is not the end. It is not even the beginning of the end. But it is, perhaps, the end of the beginning."
Anyway, these are the ongoing thoughts.
I've been thinking about my supervisor's work on the structures of political speeches and, in particular, the speeches of Churchill. The semantic and linguistic structures look so much like the structures of humour. Couplets and triplets working, often using incongruous elements, to make a memorable and surprising statement. Maybe this is why they can be so easily parodied? This leads me to question whether the application of the General Theory of Verbal Humour presupposes the intention of the script or performance. Would the GTVH give a 'false positive' if applied to "Now this is not the end. It is not even the beginning of the end. But it is, perhaps, the end of the beginning."
Anyway, these are the ongoing thoughts.
Subscribe to:
Posts (Atom)