2024 is getting off to a fabulous start with several changes in the team. First of all we welcome Yevhen Kostiuk who comes to us from Mexico City, and Ayah Soufan who had slightly less distance to travel, coming from Glasgow. They are both joining as postdoctoral researchers. We also welcome back Debela Gemechu, who finished his PhD here in 2021 and then went to work for ContactEngine (which was subsequently acquired by NICE systems) whilst remaining affiliated with ARG-tech as Industrial Fellow in Residence; he rejoins us now as a postdoctoral researcher. Finally, we’re also thrilled to see Elaine McIntyre advancing to a more senior role in supporting the operations of the Centre — anyone who has any dealings with ARG-tech will know that Elaine is a lynchpin of organisational management, so it is super to see her work recognised in this way.
So welcome to Ayah and Yevhen, welcome back to Debela, and congratulations to Elaine! 2024 is going to be a great year!
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 firstname.lastname@example.org Closing date is 23 September 2023.
ARG-tech is continuing to expand. We are looking both for candidates for PhD positions, and now also for postdoctoral research positions that are permanent subject to funding review after three years. We are looking both for junior candidates who have either just finished or are about to finish their PhD, and for more senior researchers with significant research experience (Grade 7 to Grade 8, £35,308 to £47,047).
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 degrees in philosophy, linguistics, literature, communication, cognitive science, AI, mathematics, engineering, economics, international relations, law, or any other cognate disciplines.
More details are available online, or contact the director of the Centre, Chris Reed, email@example.com. Applications are accepted online until the deadline, 14 August 2023.
We’re at the end of the first quarter of 2023 and apart from the usual ‘wow, where has the time gone?’ it’s also an opportunity to look at how the Centre has changed over the past few months. With current funding from IARPA, Dstl, AHRC, SNF, VW Stiftung, EMIF and H2020, we have been building the team and offering many welcomes in one form or another. Starting in January, Nicole Orr, who has been connected with ARG-tech since even before she started her undergraduate degree, embarked on her PhD with us. Later that month, Cameron Bryce came to us as an intern with a brief on DevOps, joining Zvony Delas and Idris Mahamdi, who between them have inaugurated our new Internship Programme. Less than a week later, Eimear Maguire came from Paris Cité to join us as a postdoc to work on computational pragmatics and models of discourse. The week after that, Godfrey Inyama fresh with his MSc from Heriot Watt, started as a PhD student working in deep learning models of dialogue. At the start of February, Suzanne Duce trekked all the way from the other side of campus to join us in helping to manage the increasing organisational workload across all of the various threads of research. Then technically on the same day, Ramon Ruiz Dolz from UPV in Valencia joined as a postdoc, but practicalities meant that it was not until today that he joins us physically in Dundee.
So it’s been a busy start to the year. But it’s exciting. The buzz in the air in our labs is palpable as work starts on several new initiatives; the vibrancy of the group is addictive. One of the things I love the most is the rapid identification of new and interesting problems and the small teams forming ad hoc to dig into them from the many disciplinary backgrounds represented here.
With this signficant uptick in the size of the team, we’re going to be able to start to tackle more and bigger problems, and to really accelerate on some of the deep challenges in argument technology. The rest of 2023 is going to be an exciting ride!
OVA3 is the latest release of the Online Visualisation of Argument analysis tool. OVA3 is thoroughly re-engineered for speed, stability and scalability and introduces collaborative editing, PDF annotation, utterance timestamps and a re-designed easy-to-use graphical interface. Like its predecessor (OVA2) it supports a wide variety of argumentation schemes and is also designed to handle both simple monological arguments and complex arguments situated in dialogue, as well as providing optional support for analysis using Inference Anchoring Theory.
OVA has tens of thousands of users and is a native Argument Web application, interfacing to annotation of millions of words across thousands of arguments through the underlying AIF representation used in a variety of AI applications including argument mining algorithms, automatic grading software and visual analytics that provide insight and summary.
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 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!