PhD Topics

If you are interested in becoming a research student (MPhil/PhD), do have a look at the topics here. If any of these appeals to you, please feel free to contact me.

Automatic Generation of Dialogue Acts: Understanding Dialogue through Computational Modelling

Dialogue Games, Argumentation and Meaning: Computational modelling of Brandom's inferentialism

From data to questions and stories: inclusive technologies for data exploration

[Back to Paul Piwek's Homepage]

Automatic Generation of Dialogue Acts: Understanding Dialogue through Computational Modelling

The purpose of this project is to gain a better understanding of human-human dialogue through formal/computational modelling (Piwek, 2011; 2006). It will focus one of the following three phenomena in dialogue:

  1. multimodal dialogue acts (involving gesture and speech) (Piwek 2009; Piwek, Beun & Cremers, 2008),
  2. generation of questions (Piwek & Boyer, 2012; Kuyten et al., 2012; Rus et al. 2010; Wyse & Piwek, 2009), or
  3. adversarial dialogue moves (and emotion) (Pluss, 2014; Pluss, Piwek & Power, 2011).

The main aim of the project will be to construct a computational model of one of these phenomena. This will involve building algorithms for automatically generating dialogue acts that exhibit the relevant phenomenon (for example, a model for automatically generating questions or, for instance, for generating multimodal dialogue acts).

The research may (or may not) involve developing a pair of agents that have the ability to converse with each other, with the resulting behaviour mirroring, in relevant respects, the human behaviours as we find them in naturally-occurring dialogues.

Skills and Background required

A good undergraduate degree (2.1 or above) in Computing (or equivalent), with experience in artificial intelligence, computational linguistics or natural language processing. A background in linguistics would also be suitable, if accompanied by a suitable computer skills.

References

Pluss, B. (2014). A computational Model of Non-cooperation in Natural Language Dialogue. PhD Thesis, The Open University, UK.

Piwek, Paul and Boyer, Kristy Elizabeth (2012). Varieties of Question Generation: introduction to this special issue. Dialogue & Discourse, 3(2), pp. 1-9.

Kuyten, Pascal; Bickmore, Timothy; Stoyanchev, Svetlana; Piwek, Paul; Prendinger, Helmut and Ishizuka, Mitsuru (2012). Fully automated generation of question-answer pairs for scripted virtual instruction. In: 12th International Conference on Intelligent Virtual Agents, 12 - 14 September 2012, Santa Cruz, CA, USA.

Piwek, Paul (2011). Three principles of information flow: conversation as a dialogue game. In: Ramage, Magnus and Chapman, David eds. Perspectives on Information. Routledge Studies in Library and Information Science (9). New York, USA: Routledge, pp. 106120.

Pluss, Brian; Piwek, Paul and Power, Richard (2011). Modelling non-cooperative dialogue: the role of conversational games and discourse obligations. In: 15th Workshop on the Semantics and Pragmatics of Dialogue, 21-23 September 2011, Los Angeles, pp. 212213.

Rus, Vasile; Wyse, Brendan; Piwek, Paul; Lintean, Mihai; Stoyanchev, Svetlana and Moldovan, Cristian (2010). The First Question Generation Shared Task Evaluation Challenge. In: Proceedings of the Sixth International Natural Language Generation Conference (INLG 2010), 7-9 July 2010, Trim Castle, Ireland.

Wyse, Brendan and Piwek, Paul (2009). Generating questions from OpenLearn study units. In: AIED 2009 Workshop Proceedings Volume 1: The 2nd Workshop on Question Generation, 6-9 July 2009, Brighton, UK.

Piwek, Paul (2009). Salience and pointing in multimodal reference. In: Proceedings of Production of Referring Expressions: Bridging the gap between computational and empirical approaches to generating reference (PRE-CogSci 2009), 29 July 2009, Amsterdam.

Piwek, Paul; Beun, Robbert-Jan and Cremers, Anita (2008). 'Proximal' and 'distal' in language and cognition: Evidence from deictic demonstratives in Dutch. Journal of Pragmatics, 40(4) pp. 694-718.

Piwek, Paul (2006). Perspectives on dialogue: Introduction to this special issue. Research on Language and Computation, 4(2-3) pp. 143-152.



Dialogue Games, Argumentation and Meaning: Computational modelling of Brandom's inferentialism

In a number of books (e.g. Brandom, 1994; Brandom, 2000), the philosopher Robert Brandom has uncovered deep connections between dialogue games and argumentation on the one hand, and meaning on the other. Some progress has been made on making these ideas computational (see e.g. Piwek, 2014). The aim of this project is to further develop and implement these computational interpretations of Brandom's work. This may include the use of visualisations in order to get a better understanding of the models. It could also lead to development of applications (e.g., in argumentation education).

Skills and Background required

A good undergraduate degree (2.1 or above) in Computing (or equivalent), with experience in logical semantics (ideally, also proof-theoretic/inferentialist approaches) and/or dialogue modelling.

References

Brandom, R. (2000). Articulating Reasons: An Introduction to Inferentialism. Cambridge, USA: Harvard University Press. http://www.hup.harvard.edu/catalog.php?isbn=9780674006928

Brandom, R. (1994). Making It Explicit: Reasoning, Representing, and Discursive Commitment. Cambridge, USA: Harvard University Press. http://www.hup.harvard.edu/catalog.php?isbn=9780674543300

Piwek, P. (2014). Towards a Computational Account of Inferentialist Meaning. Proceedings of the AISB50 Convention, Goldsmith's College London, April 3, 2014.

Piwek, Paul (2013). Supporting computing and technology distance learning students with developing argumentation skills. In: IEEE Global Engineering Education Conference (EDUCON 2013), 12-15 March 2013, Berlin.

Piwek, P. (2011). Dialogue Structure and Logical Expressivism. Synthese 183: 33-58.

Further references relating to this topic.



From data to questions and stories: inclusive technologies for data exploration

Companies, governments and citizens produce and share data on a wide variety of topics. In order to make productive and informed use of such data, they needs tools and technologies to explore these data. In particular, they could benefit from help with articulating questions that the data may address and with discovering possible stories that the data is (or perhaps isn't) telling.

We propose to use AI techniques and text generation to allow users to engage with data. For instance, the proposed technology could suggest possible questions or stories based on the data. We will focus on inclusive technologies, e.g. by linking up text generation with spoken language technologies to ensure accessibility for visually-impaired users.

We propose to use AI techniques and text generation to allow users to engage with data. For instance, the proposed technology could suggest possible questions or stories based on the data. We will focus on inclusive technologies, e.g. by linking up text generation with spoken language technologies to ensure accessibility for visually-impaired users.

Skills and background

Good undergraduate degree (2.1 or above) in Computing, ideally with experience in natural language processing.

References

NESTA-funded DataMIX project paper on inclusive data communication, EPSRC-funded CODA project on dialogue and question generation.

Blogposts by Tony Hirst on robot churnalism and book on wrangling F1 data.

Summer school tutorial by Paul Piwek at the Summer School on Natural Language Generation, Summarisation, and Dialogue Systems.

Piwek, Paul and Boyer, Kristy Elizabeth eds. (2012). Special Issue on Question Generation. Dialogue & Discourse, 3 (2). Dialogue and Discourse (D&D).