Our work with the BBC over 2018-2019 focused on helping school pupils to identify fake news by putting news articles under a critical thinking microscope. The Evidence Toolkit was rolled out to over 3,000 schools and was the first publicly deployed application to rely upon argument mining. Our work is described in an article just out in this month’s Communications of the ACM.
Many congratulations to John Lawrence, who has successfully defended his PhD thesis on Explainable Argument Mining. He was examined by Prof. Manfred Stede from Potsdam University, Prof. Rob Gaizauskas from The University of Sheffield, and Prof. Manuel Trucco from Dundee. John is staying in the group as a permanent lecturer.
This week sees the Eighth International Conference on Computational Models of Argument (COMMA 2020) and ARG-tech is well-represented at the main conference and the workshops.
Chris Reed will deliver the opening invited keynote on Argument Technology from Philosophy to Phone, charting 20 years of research into Argument Technology.
Abstract: Computational models of argument have vast potential to transform human reasoning and decision-making wherever it occurs – taking theories rooted in philosophy, developing algorithms in data science, natural language processing and AI, and engineering solutions that could end up on a phone in everyone’s pocket. Fulfilling that potential, however, is enormously challenging. Sometimes, what’s required is overhauling our most fundamental theories to accommodate real world phenomena: arguments in the real world, for example, most typically occur in multi-party contexts, so new theories have had to be developed to account for and handle dialogical, dialectical and interactional aspects of argumentation, whilst still supporting formally well-understood phenomena such as abstraction and acceptability, audiences and values, lexical semantics and argument structure.
Papers and demonstrations
Mark Snaith. An Argument-based Framework for Selecting Dialogue Move Types and Content
Rory Duthie, John Lawrence, Chris Reed, Jacky Visser and Dimitra Zografistou. Navigating Arguments and Hypotheses at Scale.
Matt Foulis, Jacky Visser and Chris Reed. Dialogical Fingerprinting of Debaters.
Iwan Ittermann and Brian Plüss. PEOPLES: From Private Responses to Messages to Depolarisation Nudges in Two-Party Adversarial Online Talk.
Mark Snaith, John Lawrence, Alison Pease and Chris Reed. A Modular Platform for Argument and Dialogue.
ArgVis 2020 workshop (co-organised by Brian Plüss and Rory Duthie)
Matt Foulis, Jacky Visser and Chris Reed. Interactive Visualisation of Debater Identification and Characteristics.
Summer School on Argumentation (SSA 2020)
Chris Reed will deliver an invited talk on Bridging the gap from linguistic to computational models of argument.
Abstract: One of the ways in which the COMMA community is composed of different threads of research is the varying extent to which use is made, on the one hand, of linguistic models, and, on the other, of formal techniques. Linguistic models have much to say about what an argument is, about how it is composed, and how it is situated in the world. Formal (both structured and abstract) models focus instead on a much narrower conception of what an argument is, and much more on one argument’s interactions with others. We have learnt that the Argument Interchange Format is an effective way of delivering data from the linguistic world and delivering computation back from the formal world, yet AIF on its own cannot handle real world data directly. This talk will summarise Inference Anchoring Theory, a technique that ties together discursive activity with formal structure, all of which can be represented in AIF and transported across the bridge to the rich formal and computational techniques.
We’re excited to announce that we have been successful in securing further funding from the Defence Science and Technology Laboratory (DSTL) to explore new ways of working with evidence to build hypotheses and challenge cognitive bias.
One key challenge to be tackled by the project is how to navigate vast networks of connected pieces of evidence that underpin new hypotheses – how to find the critical clue that constitutes the missing part of the reasoning puzzle.
The project runs until March 2021 and is delivering the first tranche of results through the coming year to the Ministry of Defence’s SERAPIS Framework, a £300m investment in defence and intelligence capability.
This new funding comes on the back of our previous DSTL-funded project on Dialogical Fingerprinting.
We’re delighted to announce that we have been successful in securing UKRI funding to help combat fake news during the COVID-19 pandemic. The project, in collaboration with Elena Musi from the University of Liverpool, aims to help the public identify “semi-fake news” and build “fake news immunity”.
“Semi-fake news” is information that uses selective existing facts, such as partial scientific results or single anecdotes, to reach false evaluations. This puts it out of the reach of most automated fact-checkers because of the lack of outright mistruths.
Work on the project starts this week, and will deliver its outcomes by the middle of 2021.
Many congratulations to Rory Duthie, who today successfully defended his PhD thesis on Mining Ethos in Parliamentary Debate. He was examined by Prof. Benno Stein from Bauhaus University, and Prof. Stephen McKenna from Dundee. After spending much of 2019 working in data analytics for HSBC, Rory has returned to the group and is now is now working as a postdoc, investigating connections between argumentation and hypotheses.
We are delighted to welcome Mark K. Smith into the group as an Honorary Professor. Mark is CEO of ContactEngine, a company specialising in conversational AI. ARG-tech and ContactEngine have been collaborating for some time now exploring ideas underpinning Human Computer Rapport, an integrated way of handling conversational context. Mark’s appointment in recognition of his leadership and insight in AI R&D represents a ramping up in this collaboration which will see close working between the two teams.
Chris was today giving evidence at the All Party Parliamentary Group on AI at the House of Lords. The focus of his contribution was on the reality of AI’s competence and the great distance that remains before AGI is imminent.
The start of the year has seen some exciting staff changes in ARG-tech. We welcome Dimitra Zografistou, who joins us from FORTH to work on models of argument representation. Rory Duthie is finishing writing up his thesis and starting to work as a research assistant on connections between argumentation and hypotheses. And finally, John Lawrence and Jacky Visser have both been appointed to permanent lectureships in the group.
We’re delighted that our survey of the field of Argument Mining is just out with Computational Linguistics. It provides the most up-to-date review currently accessible and is available now online.
Abstract. Argument Mining is the automatic identification and extraction of the structure of inference and reasoning expressed as arguments presented in natural language. Understanding argumentative structure makes it possible to determine not only what positions people are adopting, but also why they hold the opinions they do, providing valuable insights in domains as diverse as financial market prediction and public relations. This paper explores the techniques that establish the foundations for argument mining, provides a review of recent advances in argument mining techniques, and discusses the challenges faced in automatically extracting a deeper understanding of reasoning expressed in language in general.