Augmented Deliberative Democracy (ADD-up)

Election Debate Visualisation (EDV)

Non-cooperation in Dialogue (PhD Project)

My PhD research project focused on the analysis and modelling of non-cooperation in dialogue.

Conversation is usually understood as a collaborative task, in which two or more participants work together in order to achieve a certain goal. Consequently, most theories of dialogue assume full cooperation between the dialogue participants. Concepts like joint actions, shared plans or dialogue games all belong in this tradition, and a series of rather successful research dialogue systems have been implemented based on these models. They all have in common the assumption that participants agree on what they want to achieve with the conversation and that their joint efforts go in that direction. For instance, an example interaction with CMU’s Let’s Go dialogue system is available here.

However, real-life conversations go seldom so smoothly. A great many situations escape the assumptions above, in which case existing models have little to say. My PhD research aimed at narrowing this gap by looking carefully at the “odd” cases: those in which dialogue participants depart from the norm and act selfishly in pursuit of their individual goals.

The project had two main tracks: performing empirical investigations on the nature of non-cooperative conversational behaviour in naturally-occurring dialogues, and devising an adequate computational model of dialogue management towards implementing conversational agents that are able to exhibit such behaviour.

For the empirical analysis I use broadcast political interviews as a source of data. The particular nature of these exchanges, and the usually conflicting goals interviewers and politicians bring to them, provide plenty of interesting situations to work with. A few examples follow:

(Source: BBC NEWS)

(Source: BBC NEWS)

(Source: BBC NEWS)

For a details of the research approach, dataset, methods and evaluation, take a look at my thesis and supplementary materials.

Preliminary work on the kind of analysis I did on the data, is in my ACL-SRW 2010 paper Non-Cooperation in Dialogue.

For the modelling and implementation side of the project, I drew on the notions of conversational games and discourse (or social) obligations, and on how they interplay with (selfish) rational agency to produce the kind of behaviour observed in the data. You can take a look at my FLATLANDS 2011 talk slides for details on this.

If you have an interest in any of these issues and want to exchange ideas, please send me an email.

Natural Language Generation from
Formal Software Specifications

Rule-based Spell-checking for Spanish

Computational Humour