Filters








546 Hits in 6.4 sec

Measuring Societal Biases from Text Corpora with Smoothed First-Order Co-occurrence [article]

Navid Rekabsaz, Robert West, James Henderson, Allan Hanbury
2021 arXiv   pre-print
We compare these approaches by conducting several experiments on the scenario of measuring gender bias of occupational words, according to an English Wikipedia corpus.  ...  The common approach to measuring such biases using a corpus is by calculating the similarities between the embedding vector of a word (like nurse) and the vectors of the representative words of the concepts  ...  We use the discussed word representations, trained on an English Wikipedia corpus to study the characteristics of the first-and high-order bias measurement approaches.  ... 
arXiv:1812.10424v4 fatcat:irlckgvcsbbpfcnsodfvhhpgou

What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics

Antitza Dantcheva, Petros Elia, Arun Ross
2016 IEEE Transactions on Information Forensics and Security  
These attributes can be used in a fusion framework to improve the matching accuracy of a primary biometric system (e.g., fusing face with gender information), or can be used to generate qualitative descriptions  ...  In this paper, we provide an overview of soft biometrics and discuss some of the techniques that have been proposed to extract them from image and video data.  ...  Falsetti [58] and Lazenby [140] used measurements of metacarpals of the human hand and obtained gender classification rates of up to 92%. Another approach to determine the gender by Krishan et al.  ... 
doi:10.1109/tifs.2015.2480381 fatcat:rmgdjjvbznchhdeib24bfzonki

Seeing the invisible: brand authenticity and the cultural production of queer imagination

Jonatan Södergren, Niklas Vallström
2021 Arts and the Market  
PurposeThe twofold aim of this theory-building article is to raise questions about the ability of queer cinema to transform market culture and ideologies around gender and sexuality.  ...  films (Moonlight, Call Me By Your Name and Portrait of a Lady on Fire), the authors outline some profound narrative tensions addressed by movie makers seeking to give an authentic voice to queer lives.FindingsBrands  ...  Film theory has also made its way into marketing research on gender representations and other forms of resistance to cultural homogenization (e.g.  ... 
doi:10.1108/aam-12-2020-0053 fatcat:dqoz5tviefflzp64ubi7pojoya

A Little Something Goes a Long Way: Little in the Old Bailey Corpus

Claudia Claridge, Ewa Jonsson, Merja Kytö
2021 Journal of English Linguistics  
Therefore, the present paper is devoted to the structural and functional profile of ( a) little in Late Modern English speech-related data.  ...  Our research charts the semantic and formal uses of adverbial little. Downtoner uses outnumber non-degree uses in the data, and diminishing uses are more common than minimizing uses.  ...  to us.  ... 
doi:10.1177/0075424220982063 fatcat:oh5kqgri7jfprfuu5xfyts6qk4

A giant with feet of clay: on the validity of the data that feed machine learning in medicine [article]

Federico Cabitza, Davide Ciucci, Raffaele Rasoini
2018 arXiv   pre-print
To this aim, we point out how uncertainty is so ingrained in medicine that it biases also the representation of clinical phenomena, that is the very input of ML models, thus undermining the clinical significance  ...  This paper considers the use of Machine Learning (ML) in medicine by focusing on the main problem that this computational approach has been aimed at solving or at least minimizing: uncertainty.  ...  ex-post, as information bias, by comparison with an unbiased (if any) gold standard.  ... 
arXiv:1706.06838v3 fatcat:xmfzemujszb43gz4a3h3phswtm

Hippocampal development and the dissociation of cognitive-spatial mapping from motor performance

Bryan D. Devan, Christopher Magalis, Robert J. McDonald
2015 F1000Research  
This form of latent learning was interpreted as successfully demonstrating that an exploratory cognitive map component was acquired irrespective of performing a learned spatial response under deprivation  ...  Subsequent behavioral studies attempted to directly eliminate the motor component of spatial learning by allowing rats to passively view the distal environment before performing any motor response using  ...  Also, the use of an unbiased stereology technique should be considered. 8) It appears that different behavioral procedures may have been conducted at different institutions.  ... 
doi:10.12688/f1000research.6966.1 pmid:26594345 pmcid:PMC4648208 fatcat:vomchcbx7vea7a5wln33efgviq

Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions

Eike Petersen, Yannik Potdevin, Esfandiar Mohammadi, Stephan Zidowitz, Sabrina Breyer, Dirk Nowotka, Sandra Henn, Ludwig Pechmann, Martin Leucker, Philipp Rostalski, Christian Herzog
2022 IEEE Access  
Promising solution approaches include the use of large and representative datasets and federated learning as a means to that end, the careful exploitation of domain knowledge, the use of inherently transparent  ...  , and nondiscrimination are all demanded already by existing law and regulations -albeit, in many cases, to an uncertain degree.  ...  ACKNOWLEDGMENT The authors would like to thank Jannik Prüßmann, B.Sc., for assistance with the formatting of the references.  ... 
doi:10.1109/access.2022.3178382 fatcat:cwpkgkx2ibcgbdatd4aidwa4xy

Transparent to whom? No algorithmic accountability without a critical audience

Jakko Kemper, Daan Kolkman
2018 Information, Communication & Society  
We increasingly defer decisions to algorithms because machines have earned a reputation of outperforming us.  ...  Algorithms come to reflect the biases of their creators, can reinforce established ways of thinking, and may favour some political orientations over others.  ...  His research revolves around the sociology of quantification, intelligent decision support systems (e.g. machine learning, artificial intelligence), and organizational decision-making.  ... 
doi:10.1080/1369118x.2018.1477967 fatcat:xcjivc5lcnfkxaf3wozziabaxa

DeepHelp: Deep Learning for Shout Crisis Text Conversations [article]

Daniel Cahn
2021 arXiv   pre-print
Specifically, this project aims to use deep learning to (1) predict an individual's risk of suicide or self-harm, (2) assess conversation success and CV skill using robust metrics, and (3) extrapolate  ...  Finally, reversal of participation bias provides evidence that women, who make up 80.3% of conversations with an associated texter survey, make up closer to 73.5%- 74.8% of all conversations; and that  ...  Acknowledgements Thank you to Dr. Mark Ungless, Dr.  ... 
arXiv:2110.13244v1 fatcat:ka2hq4u7w5de7am666mmkyxgia

Hippocampal development and the dissociation of cognitive-spatial mapping from motor performance

Bryan D. Devan, Christopher Magalis, Robert J. McDonald
2015 F1000Research  
This form of latent learning was interpreted as successfully demonstrating that an exploratory cognitive map component was acquired irrespective of performing a learned spatial response under deprivation  ...  Subsequent behavioral studies attempted to directly eliminate the motor component of spatial learning by allowing rats to passively view the distal environment before performing any motor response using  ...  Also, the use of an unbiased stereology technique should be considered. 8) It appears that different behavioral procedures may have been conducted at different institutions.  ... 
doi:10.12688/f1000research.6966.2 pmid:26594345 pmcid:PMC4648208 fatcat:m73zbbshwrfetd4xct4n363vbe

Digital Public History Inside and Outside the Box

Enrica Salvatori
2020 magazén  
Although no digital history research centres exist in Italy nowadays, it is possible to look at several Italian projects in order to discuss the strange position of the digital issue within public history  ...  conferences, the place of history in the large digital humanities environment and finally the definition itself of digital history.  ...  The gimlet eye of reminiscence is used to curate exhibitions which represent an adult interpretation of a previous time.  ... 
doi:10.30687/mag/2724-3923/2020/02/003 fatcat:dmabtb22vrfahnkayqczgorwj4

Authors and Writing [chapter]

Martin Paul Eve
2022 The Digital Humanities and Literary Studies  
This chapter introduces a range of approaches to the measurement and digital quantification of literary style: stylometry or digital stylistics.  ...  Further covered in this first chapter are analyses of genre and its lifecycles (Ted Underwood), approaches to poetry (Tanya E.  ...  authors use different words.  ... 
doi:10.1093/oso/9780198850489.003.0002 fatcat:k2lefcj7sjab7fvxbhzhuqz4ny

Frequency and length of syllables in Serbian

Marija Radojicic, Biljana Lazic, Sebastijan Kaplar, Ranka Stankovic, Ivan Obradovic, Ján Macutek, Lívia Lessová
2019 Glottometrics  
Contributions in English or German written with a common text processing system (preferably WORD) should be sent to one of the editors.  ...  Beiträge in Deutsch oder Englisch sollten an einen der Herausgeber in einem gängigen Textverarbeitungssystem (vorrangig WORD) geschickt werden.  ...  Acknowledgments This work is supported by the University of Ostrava (No. SGS01/UVAFM/2018), the European Union & Ministry of Education of the Czech Republic (No.  ... 
dblp:journals/glottometrics/RadojicicLKSOML19 fatcat:3cdl7l4wpfaf7gq7k7kmgjktci

The Future of Affirmative Action: Reclaiming The Innovative Ideal

Susan Sturm, Lani Guinier
1996 California Law Review  
Opponents have defined affirmative action as a program of racial preferences that threatens fundamental American values of fairness, equality, and democratic opportunity.'  ...  If different approaches can be used to accomplish an underlying goal, and these differing approaches correlate with race or gender, then an employer may not fairly insist on only one of these approaches.lu  ...  Under these conditions, race-and gender-based inquiries continue to form the cornerstone of an integrated approach to a progressive economic agenda.  ... 
doi:10.2307/3480987 fatcat:kw4jclhovba4zccxk4najhgz2q

Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Technical Challenges and Solutions [article]

Eike Petersen, Yannik Potdevin, Esfandiar Mohammadi, Stephan Zidowitz, Sabrina Breyer, Dirk Nowotka, Sandra Henn, Ludwig Pechmann, Martin Leucker, Philipp Rostalski, Christian Herzog
2021 arXiv   pre-print
Important measures that may help to address these challenges include the use of large and representative datasets and federated learning as a means to that end, the careful exploitation of domain knowledge  ...  , and nondiscrimination are all demanded already by existing law and regulations - albeit, in many cases, to an uncertain degree.  ...  Acknowledgements The authors would like to thank Jannik Prüßmann, B.Sc., for assisting with the formatting of the references.  ... 
arXiv:2107.09546v1 fatcat:er3nlre7xrg4lmqsgxs7c4pswu
« Previous Showing results 1 — 15 out of 546 results