Professor Steven Bradley's Outputs (2)

Evidence for Teaching Practices that Broaden Participation for Women in Computing (2021)
Presentation / Conference Contribution
Morrison, B. B., Quinn, B. A., Bradley, S., Buffardi, K., Harrington, B., Hu, H. H., …Waite, J. (2021). Evidence for Teaching Practices that Broaden Participation for Women in Computing. In ITiCSE-WGR '21: Proceedings of the 2021 Working Group Reports on Innovation and Technology in Computer Science Education (57-131). https://doi.org/10.1145/3502870.3506568

Computing has, for many years, been one of the least demographically diverse STEM fields, particularly in terms of women's participation [12, 36]. The last decade has seen a proliferation of research exploring new teaching techniques and their effect... Read More about Evidence for Teaching Practices that Broaden Participation for Women in Computing.

ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference (2021)
Book Chapter
Gajbhiye, A., Al Moubayed, N., & Bradley, S. (2021). ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference. In I. Farkaš, P. Masulli, S. Otte, & S. Wermter (Eds.), Artificial Neural Networks and Machine Learning – ICANN 2021 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 14–17, 2021, Proceedings, Part V (460-472). Springer Verlag. https://doi.org/10.1007/978-3-030-86383-8_37

Neural language representation models such as BERT, pretrained on large-scale unstructured corpora lack explicit grounding to real-world commonsense knowledge and are often unable to remember facts required for reasoning and inference. Natural Langua... Read More about ExBERT: An External Knowledge Enhanced BERT for Natural Language Inference.