Computational Argumentation-based Chatbots: A Survey
Authors: Federico Castagna, Nadin Kökciyan, Isabel Sassoon, Simon Parsons, Elizabeth Sklar
JAIR 2024 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The present survey sifts through the literature to review papers concerning this kind of argumentation-based bot, drawing conclusions about the benefits and drawbacks that this approach entails in comparison with standard chatbots, while also envisaging possible future development and integration with the Transformer-based architecture and state-of-the-art Large Language Models. Our main contribution involves an extensive examination of the relevant literature and the subsequent findings that can be drawn from such analysis. |
| Researcher Affiliation | Academia | Federico Castagna EMAIL Brunel University London, Kingston Lane, London, UB8 3PH, United Kingdom Nadin K okciyan EMAIL University of Edinburgh, Crichton St, Edinburgh EH8 9AB, United Kingdom Isabel Sassoon EMAIL Brunel University London, Kingston Lane, London, UB8 3PH, United Kingdom Simon Parsons EMAIL Elizabeth Sklar EMAIL University of Lincoln, Brayford Pool, Lincoln, LN6 7TS, United Kingdom |
| Pseudocode | No | The paper describes systems from other works, such as the 'ASP-Solver ASPARTIX' as an example of an argumentation-driven reasoning engine, but does not present pseudocode or algorithm blocks for its own survey methodology. |
| Open Source Code | No | The paper discusses various software tools and platforms (e.g., IBM Watson, Google Dialog Flow) that are employed by the argumentation-based chatbots it reviews, and references existing solvers like AFGCN, A-Folio DPDB, and ASPARTIX-V21. However, it does not provide concrete access to source code for the methodology of this survey paper itself. |
| Open Datasets | No | The paper references datasets and corpuses used by other argumentation-based chatbots, such as 'movie review snippets' or 'a corpus of 400 million newspaper articles' for argument mining, and presents an example of text analysis. However, it does not provide concrete access information (link, DOI, repository, or formal citation) for a dataset used in the context of this survey itself. |
| Dataset Splits | No | This paper is a survey and does not present original experimental work requiring dataset splits. Therefore, no information on training/test/validation splits is provided for its own research. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts) used for conducting its research. As a survey, it focuses on reviewing existing literature rather than experimental computation. |
| Software Dependencies | No | The paper discusses various software tools and platforms (e.g., IBM Watson, Google Dialog Flow) that are employed by the argumentation-based chatbots it reviews. However, it does not provide specific ancillary software details with version numbers for the methodology of this survey itself. |
| Experiment Setup | No | This paper is a survey and does not describe experimental work with specific hyperparameters or training configurations. Therefore, no details about an experimental setup are provided. |