Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Sabry, Sana Sabah"'
We introduce bipol, a new metric with explainability, for estimating social bias in text data. Harmful bias is prevalent in many online sources of data that are used for training machine learning (ML) models. In a step to address this challenge we cr
Externí odkaz:
http://arxiv.org/abs/2304.04029
Autor:
Adewumi, Tosin, Södergren, Isabella, Alkhaled, Lama, Sabry, Sana Sabah, Liwicki, Foteini, Liwicki, Marcus
We investigate five English NLP benchmark datasets (on the superGLUE leaderboard) and two Swedish datasets for bias, along multiple axes. The datasets are the following: Boolean Question (Boolq), CommitmentBank (CB), Winograd Schema Challenge (WSC),
Externí odkaz:
http://arxiv.org/abs/2301.12139
We conduct relatively extensive investigations of automatic hate speech (HS) detection using different state-of-the-art (SoTA) baselines over 11 subtasks of 6 different datasets. Our motivation is to determine which of the recent SoTA models is best
Externí odkaz:
http://arxiv.org/abs/2210.05480
Autor:
Sabry, Sana Sabah, Adewumi, Tosin, Abid, Nosheen, Kovacs, György, Liwicki, Foteini, Liwicki, Marcus
We investigate the performance of a state-of-the art (SoTA) architecture T5 (available on the SuperGLUE) and compare with it 3 other previous SoTA architectures across 5 different tasks from 2 relatively diverse datasets. The datasets are diverse in
Externí odkaz:
http://arxiv.org/abs/2202.05690
Autor:
Adewumi, Tosin, Brännvall, Rickard, Abid, Nosheen, Pahlavan, Maryam, Sabry, Sana Sabah, Liwicki, Foteini, Liwicki, Marcus
Building open-domain conversational systems (or chatbots) that produce convincing responses is a recognized challenge. Recent state-of-the-art (SoTA) transformer-based models for the generation of natural language dialogue have demonstrated impressiv
Externí odkaz:
http://arxiv.org/abs/2110.06273
Autor:
Adewumi, Tosin1 (AUTHOR) sana.al-azzawi@ltu.se, Sabry, Sana Sabah1 (AUTHOR), Abid, Nosheen1 (AUTHOR), Liwicki, Foteini1 (AUTHOR), Liwicki, Marcus1 (AUTHOR)
Publikováno v:
Sci. Dec2023, Vol. 5 Issue 4, p37. 17p.
Publikováno v:
International Journal of Emerging Technologies in Learning; 2020, Vol. 15 Issue 9, p110-122, 13p