Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Sundaram, Sowmya"'
Autor:
Sundaram, Sowmya S, Alwar, Balaji
The prevalence of unwarranted beliefs, spanning pseudoscience, logical fallacies, and conspiracy theories, presents substantial societal hurdles and the risk of disseminating misinformation. Utilizing established psychometric assessments, this study
Externí odkaz:
http://arxiv.org/abs/2405.00843
Autor:
Sundaram, Sowmya S., Solomon, Benjamin, Khatri, Avani, Laumas, Anisha, Khatri, Purvesh, Musen, Mark A.
Metadata play a crucial role in ensuring the findability, accessibility, interoperability, and reusability of datasets. This paper investigates the potential of large language models (LLMs), specifically GPT-4, to improve adherence to metadata standa
Externí odkaz:
http://arxiv.org/abs/2404.05893
Publikováno v:
Frontiers in Artificial Intelligence and Applications, Volume 372: ECAI 2023
Large-scale language models such as DNABert and LOGO aim to learn optimal gene representations and are trained on the entire Human Reference Genome. However, standard tokenization schemes involve a simple sliding window of tokens like k-mers that do
Externí odkaz:
http://arxiv.org/abs/2307.15933
Autor:
Sundaram, Sowmya S., Musen, Mark A.
Publikováno v:
DaMaLOS 2023
With the global increase in experimental data artifacts, harnessing them in a unified fashion leads to a major stumbling block - bad metadata. To bridge this gap, this work presents a Natural Language Processing (NLP) informed application, called FAI
Externí odkaz:
http://arxiv.org/abs/2307.13085
Why are NLP Models Fumbling at Elementary Math? A Survey of Deep Learning based Word Problem Solvers
From the latter half of the last decade, there has been a growing interest in developing algorithms for automatically solving mathematical word problems (MWP). It is a challenging and unique task that demands blending surface level text pattern recog
Externí odkaz:
http://arxiv.org/abs/2205.15683
Autor:
P, Deepak, Sundaram, Sowmya S
Publikováno v:
Data Mining and Knowledge Discovery 37, 1374 - 1403 (2023)
Pervasiveness of tracking devices and enhanced availability of spatially located data has deepened interest in using them for various policy interventions, through computational data analysis tasks such as spatial hot spot detection. In this paper, w
Externí odkaz:
http://arxiv.org/abs/2106.06049
A clustering may be considered as fair on pre-specified sensitive attributes if the proportions of sensitive attribute groups in each cluster reflect that in the dataset. In this paper, we consider the task of fair clustering for scenarios involving
Externí odkaz:
http://arxiv.org/abs/1910.05113
Autor:
Sundaram, Sowmya S.1 (AUTHOR) sowmyassundaram@gmail.com, Gurajada, Sairam2 (AUTHOR), Padmanabhan, Deepak3 (AUTHOR), Abraham, Savitha Sam4 (AUTHOR), Fisichella, Marco1 (AUTHOR)
Publikováno v:
WIREs: Data Mining & Knowledge Discovery. Jul2024, Vol. 14 Issue 4, p1-27. 27p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
P., Deepak, Sundaram, Sowmya S.
Publikováno v:
Data Mining & Knowledge Discovery; Jul2023, Vol. 37 Issue 4, p1374-1403, 30p