ARG-tech will be present this year in Singapore at EMNLP 2023 and the 10th Workshop on Argument Mining. Two papers co-authored by ARG-tech members have been accepted to the EMNLP Main Conference and one paper to the Workshop on Argument Mining.

In the EMNLP long paper titled ‘Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks’ and co-authored by Ramon Ruiz-Dolz, we propose a hybrid method that combines concepts from Computational Argumentation theory and Natural Language Processing to predict the outcome of complete debates in academic debate tournaments.

In the EMNLP short paper titled ‘VivesDebate-Speech: A Corpus of Spoken Argumentation to Leverage Audio Features for Argument Mining’, we publicly release the largest speech corpus containing argument annotations. In addition to the corpus, initial results on the task of argument mining from spoken data are reported, pointing out that acoustic features can be a relevant addition to textual features in the segmentation of argumentative components.

Finally, in the Argument Mining Workshop paper titled ‘Detecting Argumentative Fallacies in the Wild: Problems and Limitations of Large Language Models’ and authored by Ramon Ruiz-Dolz and John Lawrence, we explore the limitations of the existing approaches to identify fallacies with state-of-the-art LLMs. We conduct an error analysis considering specific instances of arguments and rise a discussion in which we suggest the use of more complete models of argumentation that can make possible to overcome the limitations of the state-of-the-art LLMs.

In addition to advertising a permanent research position (see arg.tech/2023PDRA01) the Centre for Argument Technology is now also opening a call for applications for fully-funded PhD studentships.

We currently run a portfolio of research projects for government, charity and commercial funders in the UK, US, EU, Germany, Portugal and Switzerland worth over £1m per year and with many dependencies between these projects, we need people to join the team and help drive forward the research of the Centre. This is a unique opportunity for someone with interest and expertise in working with argumentation to join a world-leading research group – regardless of their disciplinary background. If you think you would be a good fit, we would be keen to hear from you regardless of whether you have a first degree in philosophy, linguistics, literature, communication, cognitive science, AI, mathematics, engineering, economics, international relations, law, or any other cognate disciplines.

Applications are invited across the full range of interdisciplinary research in the Centre, with more details available online.

Applications are accepted by sending cover letter and CV to jobs@arg.tech Closing date is 23 September 2023.

The annual event of the European Media and Information Fund, EMIF, coordinated by the Calouste Gulbenkian Foundation and the European University Institute, marks the start of our project on fact-checking beyond the facts: leveraging argument technology for impartial fact-checking, in collaboration with our partners led by Elena Musia at the University of Liverpool, Andrea Nicolai at T3 Systems and Gianni Riotta at LUISS in Rome.

We welcome today Somaye Moslemnejad who joins us as a new PhD student to work on algorithms for argument mining. Somaye comes to us from Mashad in Iran where she worked on machine learning applications and uncertainty, and she’ll be building on our work in deep learning and neurosymbolic argument mining.

We are excited to be getting down to work today on a project funded by the Swiss National Science Foundation lead by Andrea Rocci at USI in Lugano.

We are going to be working on the argumentation dynamics in Earnings Conference Calls, a rich source of subtle and high-impact argument in the financial domain. With a particular focus on the ways that questions generate argumentative structures, the research builds on recent work that has established methodology, coupled with recent results in argument mining. It’s going to be fun!

The Centre for Argument Technology has secured several new research funding successes in the areas of enhancing participatory democracy, protecting privacy, countering disinformation and supporting the work of the intelligence community. As a result we currently have four new vacancies:

– A Research Project Manager at Grade 7 or 8 (£34,308 to £51,805 + 21% superannuation), depending on experience. This position is open to candidates with a PhD in *any* field (www.arg.tech/2022PDRA05).

– A Postdoctoral Research Associate in computational models of dialogue at Grade 7 (£34,308 to £42,155 + 21% superannuation; www.arg.tech/2022PDRA04).

– Two PhD studentships open to candidates from anywhere in the world with full scholarship plus stipend (www.arg.tech/2022PHD04) in argument analysis, mining, representation, navigation, manipulation and visualisation.

Closing date for all positions is 20 November 2022. Details on how to apply can be found at arg.tech/vacancies. Enquiries should be addressed to the director of the Centre, Prof. Chris Reed at chris@arg.tech.

A multi-million-dollar project to protect a person’s online identity is enlisting help from ARG-tech to develop software capable of detecting and disguising trademark linguistic patterns used by individuals online.

ARG-tech are receiving $2.5m of funding as part of a larger project consortium led by SRI International in California. The project is funded by the Intelligence Advanced Research Projects Activity (IARPA), the research and development arm of the United States Government’s Office of the Director of National Intelligence.

The Dundee research forms part of IARPA’s Human Interpretable Attribution of Text Using Underlying Structure (HIATUS) program, a research effort aimed at advancing human language technology. The goals of the initiative are to help protect the identities of authors who could be endangered for speaking out, as well as developing means of identifying counterintelligence risks.

ARG-tech will utilise dialogical fingerprinting throughout the project: cutting-edge artificial intelligence technology processing dialogue models dating back centuries to develop a complete understanding of linguistic patterns.

A full Press Release is available at http://arg.tech/signature-pr.