Dialogue Systems for Synthetic Characters
Language as used is wonderfully messy. We use metaphor, we allude, we
sing and we swear. As Wittgenstein discovered, FOPC is not going
to tell us much about language in use. What we need is a model
Language as Action in a Social Setting.
Representation and information based models of language are okay as
far as they go, but something more is needed. Franco
was an ECA (Embodied Conversational Agent) in
a data cave for which we did some preliminary Wizard of Oz style
experiments (more). The conclusion then was
that we needed to know more about politeness.
Dialog at Sheffield
I was initially drawn to Sheffield to work with Yorick Wilks - someone
I had admired since my PhD days and working with LDOCE. I worked
on the proposal for Companions (and it's unsuccessful predecessor
Copain) and spend a few months working for Yorick before deciding
that it was all too hard.
I did however do some preliminary work with him as part of the Humaine NoE.
Nigel the Cuttlefish is a chatbot that uses colour to express
emotion. He uses the Belief, Desire and Intention agent architecture
to balance reactive behaviour (answering questions, greetings etc) with
deliberative behaviour (planning to get compliments for example).
Nigel uses Information extraction techniques to understand the user's
utterances, and templates to generate text - he is not that sophisticated,
but using BDI as the dialogue manager means he is more believable than many
chatbots. (see the discussion of believability here).
In 2005/6 some of us thought to look at why people abuse chatbots
My take on it is that language in use is social interaction, and that
politeness and abuse are two extremes in the maintenance of normative systems
Language has of course been studied for a long time by people outside
AI :-) and Mark Hepple
and I set up an EPSRC project to look at Conversation Analysis.
The conclusions from the CA4NLP
project (EPSRC: Engineering Natural Language Interfaces: can CA help?)
were as follows:
These results are unpublished, but not from lack of trying. I
have also done some independent work re-evaluating the DARPA Communicator data from a CA perspective.
- The CA notion of adjacency pair is indeed well founded (95%
inter-annotator agreement) but the CA community usually don't bother
with the details.
- We reproduced Skantze's map
task experiments and asked the CA people to
take a look. They need more guidance as to what we are actually
looking for - not that we know of course.
The scene in which the dog attacks the AIBO (
The key thing to come out of the CA-EM literature for me was however
Paul Seedhouse's overview of lessons learned from CA, and his overview
provides an explanation for why people swear at chatbots.
The blury picture to the right is taken from a movie of
dog attacking an AIBO. The critical point for me is that the
dog warns the robot twice before throwing it across the room
(the yelling is apparently the researchers worried about their AIBO -
it is okay by the way if you were worried to). Why does the
dog warn, and how is the AIBO meant to know that it is being warned?
The hypothesis is that the dog is using a species specific
hard-wired behavioural norm to socialize the AIBO. If the AIBO
had been a puppy, the puppy would be hard-wired to understand the
significance of the bared teeth and the growl, and would learn
to not interrupt a dominant dog's meal.
Are there human equivalents of these species specific hard-wired
behavioural norms? Yep. Seedhouse summarises the last
50 years of CA research with the high level observation that an
utterance in a conversation will either
go seen but unnoticed - people answer your questions and greet when greeted, or noticed and accounted for - you can figure out why he or she said what they said, or risks sanction.
When people abuse chatbots, the chatbot is being sanctioned. Like the
Dog in the move, we humans are hard-wired to socialize the socially
And now ...
The latest is the SERA project, which
attempts to look at the very broad picture of social engagement
of humans with synthetic characters, and give us a theoretical
framework on which to pin politeness and roles, abuse and normative