anlausch/aq_bert_ibm

Model trained on IBMArgRank30k for 2 epochs with a learning rate of 3e-5 (optimised via grid search) in a similar way as in Lauscher et al. 2020 (see below). The original model was Tensorflow-based. This model corresponds to a reimplementation with Transformers & PyTorch.

@inproceedings{lauscher-etal-2020-rhetoric,
    title = "Rhetoric, Logic, and Dialectic: Advancing Theory-based Argument Quality Assessment in Natural Language Processing",
    author = "Lauscher, Anne  and
      Ng, Lily  and
      Napoles, Courtney  and
      Tetreault, Joel",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://aclanthology.org/2020.coling-main.402",
    doi = "10.18653/v1/2020.coling-main.402",
    pages = "4563--4574",
    abstract = "Though preceding work in computational argument quality (AQ) mostly focuses on assessing overall AQ, researchers agree that writers would benefit from feedback targeting individual dimensions of argumentation theory. However, a large-scale theory-based corpus and corresponding computational models are missing. We fill this gap by conducting an extensive analysis covering three diverse domains of online argumentative writing and presenting GAQCorpus: the first large-scale English multi-domain (community Q{\&}A forums, debate forums, review forums) corpus annotated with theory-based AQ scores. We then propose the first computational approaches to theory-based assessment, which can serve as strong baselines for future work. We demonstrate the feasibility of large-scale AQ annotation, show that exploiting relations between dimensions yields performance improvements, and explore the synergies between theory-based prediction and practical AQ assessment.",
}