Filters








1,673 Hits in 7.8 sec

Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance [article]

Joshua R. Minot, Nicholas Cheney, Marc Maier, Danne C. Elbers, Christopher M. Danforth, Peter Sheridan Dodds
<span title="2021-03-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This work outlines an interpretable approach for using data augmentation to identify and reduce the potential for bias in natural language processing pipelines.  ...  We show minimal degradation in health condition classification tasks for low- to medium-levels of bias removal via data augmentation.  ...  CONCLUDING REMARKS Here we present interpretable methods for detecting and reducing bias in text data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.05841v1">arXiv:2103.05841v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nx6px3zlv5fljk3oqp7auucuee">fatcat:nx6px3zlv5fljk3oqp7auucuee</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210410025722/https://arxiv.org/pdf/2103.05841v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/89/94/8994bce4b85a8b4087584661c49f8776f868f7dd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.05841v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Interpretable bias mitigation for textual data: Reducing genderization in patient notes while maintaining classification performance

Joshua R. Minot, Nicholas Cheney, Marc Maier, Danne C. Elbers, Christopher M. Danforth, Peter Sheridan Dodds
<span title="2022-04-21">2022</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wr4frlp2lzfj5jttqy6ndk4xpm" style="color: black;">ACM Transactions on Computing for Healthcare</a> </i> &nbsp;
This work outlines an interpretable approach for using data augmentation to identify and reduce biases in natural language processing pipelines.  ...  We show minimal degradation in health condition classification tasks for low- to medium-levels of dataset bias removal via data augmentation.  ...  ACKNOWLEDGMENTS The authors are grateful for the computing resources provided by the Vermont Advanced Computing Core and inancial support from the Massachusetts Mutual Life Insurance Company and Google  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3524887">doi:10.1145/3524887</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u5alsltfyvflhbgvwzljauyirq">fatcat:u5alsltfyvflhbgvwzljauyirq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220520115948/https://dl.acm.org/doi/pdf/10.1145/3524887" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/88/e3/88e34519ab0bb22b1d7eadf53e64adfbf596069a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3524887"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Strategies for Handling Missing Data in Electronic Health Record Derived Data

Brian J. Wells, Amy S. Nowacki, Kevin Chagin, Michael W. Kattan
<span title="2013-12-17">2013</span> <i title="Ubiquity Press, Ltd."> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/atzllj4rdbc2bktp5iy4jeaeuu" style="color: black;">eGEMs</a> </i> &nbsp;
The broad range of variables available in typical EHR systems provide a wealth of information for mitigating potential biases caused by missing data.  ...  Approaches for reducing missing data in EHR systems come from multiple angles, including: increasing structured data documentation, reducing data input errors, and utilization of text parsing / natural  ...  Here, any piece of data is just as likely to be missing as any other piece of data and, while one may lose power for the analysis, the estimated parameters are not biased by absence of the data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.13063/2327-9214.1035">doi:10.13063/2327-9214.1035</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/25848578">pmid:25848578</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4371484/">pmcid:PMC4371484</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/z275fnzkxbbjfamhmyudfiyvyi">fatcat:z275fnzkxbbjfamhmyudfiyvyi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190303053454/http://pdfs.semanticscholar.org/b021/b9fc3bef24a3769098f9b7e3b2fa25ae7f63.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b0/21/b021b9fc3bef24a3769098f9b7e3b2fa25ae7f63.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.13063/2327-9214.1035"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4371484" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Biases in Data Science Lifecycle [article]

Dinh-An Ho, Oya Beyan
<span title="2020-10-27">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The aim of early publishing is to collect community feedback and improve the curated knowledge base for bias types and solutions.  ...  and mitigated if possible.  ...  And then present a collection of sources of biases in each phase with an example and with best practices for mitigating them.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09795v2">arXiv:2009.09795v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rdo67rpt7bd3hecegejk7kv3oe">fatcat:rdo67rpt7bd3hecegejk7kv3oe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929115221/https://arxiv.org/ftp/arxiv/papers/2009/2009.09795.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09795v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Attributing Fair Decisions with Attention Interventions [article]

Ninareh Mehrabi, Umang Gupta, Fred Morstatter, Greg Ver Steeg, Aram Galstyan
<span title="2021-09-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We demonstrate the versatility of our approach by conducting experiments on two distinct data types, tabular and textual.  ...  Using this attribution framework, we then design a post-processing bias mitigation strategy and compare it with a suite of baselines.  ...  We consider the biosbias dataset (De-Arteaga et al. 2019), and use our mitigation technique to reduce observed biases in the classification task performed on this dataset.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03952v1">arXiv:2109.03952v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/idqnnpvomfg3vi2nv3gvmfclom">fatcat:idqnnpvomfg3vi2nv3gvmfclom</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210915160258/https://arxiv.org/pdf/2109.03952v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c3/8a/c38a3fe6d90755faa77ec73a38bf98faa03d97a9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03952v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Data Mining Techniques in Pharmacovigilance: Analysis of the Publicly Accessible FDA Adverse Event Reporting System (AERS) [chapter]

Elisabetta Poluzzi, Emanuel Raschi, Carlo Piccinni, Fabrizio De
<span title="2012-08-29">2012</span> <i title="InTech"> Data Mining Applications in Engineering and Medicine </i> &nbsp;
Data Mining Techniques in Pharmacovigilance: Analysis of the Publicly Accessible FDA Adverse Event Reporting System (AERS) 267 tools makes them valuable sources for data mining aimed to address clinical  ...  These data can be equally useful for both aims (1 and 2 above), provided that their intrinsic limitations are duly acknowledged, in particular it should be recognized that information on outcomes are not  ...  Acknowledgments We thank Ariola Koci, statistician working at the Department of Medical and Surgical Sciences, University of Bologna for assistance in data management.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5772/50095">doi:10.5772/50095</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/clp3ldmcqfg5fbst7q2pbgs7xm">fatcat:clp3ldmcqfg5fbst7q2pbgs7xm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180727192744/https://api.intechopen.com/chapter/pdf-download/38579" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dd/07/dd0749ab211d5909d72784fa7c187e4fc15485fe.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5772/50095"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries

Alexandra Olteanu, Carlos Castillo, Fernando Diaz, Emre Kıcıman
<span title="2019-07-11">2019</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/zsdtezgyevhsxncisld4z5oxfe" style="color: black;">Frontiers in Big Data</a> </i> &nbsp;
Many academics and practitioners have warned against the naïve usage of social data. There are biases and inaccuracies occurring at the source of the data, but also introduced during processing.  ...  We identify a variety of menaces in the practices around social data use, and organize them in a framework that helps to identify them.  ...  ACKNOWLEDGMENTS We are grateful to Jisun An, Cody Buntain, Kate Crawford, Yelena Mejova, Kush Varshney, Claudia Wagner, and Ingmar Weber for detailed and insightful feedback on earlier versions of this  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fdata.2019.00013">doi:10.3389/fdata.2019.00013</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33693336">pmid:33693336</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7931947/">pmcid:PMC7931947</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yhvqij6yyvhjjcwt7u4h6oq6au">fatcat:yhvqij6yyvhjjcwt7u4h6oq6au</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200209032518/https://fjfsdata01prod.blob.core.windows.net/articles/files/456527/pubmed-zip/.versions/1/.package-entries/fdata-02-00013/fdata-02-00013.pdf?sv=2015-12-11&amp;sr=b&amp;sig=v6yBeoaEVLXodRQr7JtYCXe%2B8%2FyXCmTqzlpVpusyJqU%3D&amp;se=2020-02-09T03%3A25%3A48Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27fdata-02-00013.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/75/8a/758a29b97b416ef718daa8b4e6be672e13af1d2e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fdata.2019.00013"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7931947" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries

Alexandra Olteanu, Carlos Castillo, Fernando Diaz, Emre Kiciman
<span title="">2016</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tol7woxlqjeg5bmzadeg6qrg3e" style="color: black;">Social Science Research Network</a> </i> &nbsp;
We present a framework for identifying a broad range of menaces in the research and practices around social data.  ...  Many academics and practitioners have warned against the naïve usage of social data. There are biases and inaccuracies at the source of the data, but also introduced during processing.  ...  For instance, automatic classification, a common operation of this kind, can introduce biases in the data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2139/ssrn.2886526">doi:10.2139/ssrn.2886526</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/urp4unvmsbgnpfsg46g75ywjxy">fatcat:urp4unvmsbgnpfsg46g75ywjxy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200322095332/https://www.microsoft.com/en-us/research/wp-content/uploads/2017/03/SSRN-id2886526.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/14/3c/143c0caaa1eb79a59a8422d392459bd303268d1f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2139/ssrn.2886526"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ssrn.com </button> </a>

From the Digital Data Revolution toward a Digital Society: Pervasiveness of Artificial Intelligence

Frank Emmert-Streib
<span title="2021-03-04">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tjwucdga6zfftlebfsmbvxjiyy" style="color: black;">Machine Learning and Knowledge Extraction</a> </i> &nbsp;
enable the processing of large amounts of text data from diverse sources such as governmental reports, blog entries in social media or clinical health records of patients.  ...  This opens unprecedented opportunities but also challenges toward the analysis, management, interpretation and responsible usage of such data.  ...  The founding sponsors had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and in the decision to publish the results.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/make3010014">doi:10.3390/make3010014</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4n6em3jedzg37ltdc5eesdxnza">fatcat:4n6em3jedzg37ltdc5eesdxnza</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210319011234/https://res.mdpi.com/d_attachment/make/make-03-00014/article_deploy/make-03-00014-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d4/74/d47422ba3893708af07ca841901c3987e7a233ff.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/make3010014"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Using BiLSTM Networks for Context-Aware Deep Sensitivity Labelling on Conversational Data

Antreas Pogiatzis, Georgios Samakovitis
<span title="2020-12-14">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/smrngspzhzce7dy6ofycrfxbim" style="color: black;">Applied Sciences</a> </i> &nbsp;
We train our model on a synthetic annotated dataset of real-world conversational data categorised in 13 sensitivity classes that we derive from the P3P standard.  ...  data (multi-class sensitivity labelling).  ...  while mitigating any sensitivity class imbalances.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app10248924">doi:10.3390/app10248924</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7azezpthcjddhe6djken52p53q">fatcat:7azezpthcjddhe6djken52p53q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201219173118/https://res.mdpi.com/d_attachment/applsci/applsci-10-08924/article_deploy/applsci-10-08924-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ab/01/ab01bf2c5fb02774c21ec39c4b7b189d38bc1cca.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app10248924"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Deep Neural Networks and Tabular Data: A Survey [article]

Vadim Borisov, Tobias Leemann, Kathrin Seßler, Johannes Haug, Martin Pawelczyk, Gjergji Kasneci
<span title="2022-02-21">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To the best of our knowledge, this is the first in-depth look at deep learning approaches for tabular data.  ...  This work can serve as a valuable starting point and guide for researchers and practitioners interested in deep learning with tabular data.  ...  For instance, the data transformations can result in performance improvements while maintaining the current model architecture.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.01889v2">arXiv:2110.01889v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/65babgxtgvekbhz5mgtbnqe5by">fatcat:65babgxtgvekbhz5mgtbnqe5by</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211007041411/https://arxiv.org/pdf/2110.01889v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a2/6e/a26e8f6118d986a68c135ae94a034b2e85b32ac3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.01889v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection [article]

Shauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton, Yoav Goldberg
<span title="2020-04-28">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
While applicable for multiple uses, we evaluate our method on bias and fairness use-cases, and show that our method is able to mitigate bias in word embeddings, as well as to increase fairness in a setting  ...  The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models.  ...  Acknowledgements We thank Jacob Goldberger and Jonathan Berant for fruitful discussions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.07667v2">arXiv:2004.07667v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o66eqjzeovehzfpznvllp6eiha">fatcat:o66eqjzeovehzfpznvllp6eiha</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200504011418/https://arxiv.org/pdf/2004.07667v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.07667v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Multi-Lingually Applicable Journalist Toolset For The Big-Data Era

G. Kiomourtzis, G. Giannakopoulos, V. Karkaletsis, A. Kosmopoulos
<span title="2016-07-10">2016</span> <i title="Zenodo"> Zenodo </i> &nbsp;
In IJCAI proceedings. Workshop: Natural Language Processing meets Journalism  ...  This research was supported in part by a Discovery and Innovation Research Seed award from the Office of the Vice Provost for Research at Cornell.  ...  Acknowledgments We thank the anonymous reviewers and the participants in the Fall 2015 edition of the course "Natural Language Processing and Social Interaction" for helpful comments and discussion.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.1242850">doi:10.5281/zenodo.1242850</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nfkqg7jhjffdvgezdjzc6xxppa">fatcat:nfkqg7jhjffdvgezdjzc6xxppa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201226174032/https://zenodo.org/record/1242850/files/IJCAI2016-Proceedings.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4b/18/4b18b33c580ae384d935b9d992343609e3b94907.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.1242850"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Data Leakage Prevention for Secure Cross-Domain Information Exchange

Kyrre Wahl Kongsgard, Nils Agne Nordbotten, Federico Mancini, Raymond Haakseth, Paal E. Engelstad
<span title="">2017</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/risok53fz5a7tj5f2bczy5zmpq" style="color: black;">IEEE Communications Magazine</a> </i> &nbsp;
SVM, for instance, is known to have notoriously poor interpretability, as noted by Kotsiantis [8] .  ...  (We also note that Lasso performs better than SVM, as discussed in more detail in Section 3.3 below).  ...  In order to provide a better context for performing classification, we monitor the incoming information flow and use the audit trail to construct controlled environments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mcom.2017.1700235">doi:10.1109/mcom.2017.1700235</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zwcixu2adrgnpgtkaxg4p5kxh4">fatcat:zwcixu2adrgnpgtkaxg4p5kxh4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190501143337/https://www.duo.uio.no/bitstream/handle/10852/59409/PhD-Kongsgard-DUO.pdf?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a3/35/a3356001a860659f05e2460d707ae38761cecb81.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mcom.2017.1700235"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
<span title="2022-05-06">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we target data documentation debt by surveying over two hundred datasets employed in algorithmic fairness research, and producing standardized and searchable documentation for each of them  ...  Data-driven algorithms are studied in diverse domains to support critical decisions, directly impacting people's well-being.  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc Behaghel, Asia Biega, Marko Bohanec, Chris  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.01711v2">arXiv:2202.01711v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5hf4a42pubc5vnt7tw3al4m5bq">fatcat:5hf4a42pubc5vnt7tw3al4m5bq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220510061614/https://arxiv.org/pdf/2202.01711v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/91/57/9157d70f2c3204c064712f70a021455e4e4fb88b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.01711v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 1,673 results