Filters








4,802 Hits in 7.6 sec

Language (Technology) is Power: A Critical Survey of "Bias" in NLP [article]

Su Lin Blodgett and Solon Barocas and Hal Daumé III and Hanna Wallach
2020 arXiv   pre-print
Based on these findings, we describe the beginnings of a path forward by proposing three recommendations that should guide work analyzing "bias" in NLP systems.  ...  These recommendations rest on a greater recognition of the relationships between language and social hierarchies, encouraging researchers and practitioners to articulate their conceptualizations of "bias  ...  We excluded from the "Vague/unstated" category of motivations the papers that participated in the Gendered Ambiguous Pronoun (GAP) Shared Task at the First ACL Workshop on Gender Bias in NLP.  ... 
arXiv:2005.14050v2 fatcat:nyzr4fj5gne55jzhzm2fy5xeqa

Popularity Bias in Recommendation: A Multi-stakeholder Perspective [article]

Himan Abdollahpouri
2020 arXiv   pre-print
In addition, I propose several algorithms each approaching the popularity bias mitigation from a different angle and compare their performances using several metrics with some other state-of-the-art approaches  ...  Traditionally, especially in academic research in recommender systems, the focus has been solely on the satisfaction of the end-user.  ...  Abdollahpouri, Himan, and Masoud Mansoury. "Multi-sided Exposure Bias in Recommendation." Workshop on Industrial Recommendation Systems (IRS), in Conjunction with KDD 2020.  ... 
arXiv:2008.08551v1 fatcat:yiuamp6lcnc2bmhzkklakq6ui4

Investigating Bias in Facial Analysis Systems: A Systematic Review

Ashraf Khalil, Soha Glal, Asad Khattak, Nabeel Al-Qirim
2020 IEEE Access  
The bias can be traced in some cases to the algorithms used and in other cases to insufficient training of algorithms, while in still other cases bias can be traced to insufficient databases.  ...  The review, involving 24 studies, additionally aims to identify (a) facial analysis databases that were created to alleviate bias, (b) the full range of bias in facial analysis software and (c) algorithms  ...  For instance, in an international beauty contest launched in 2016, Beauty.AI, an automatic face analysis system was used to identify the most attractive contestants based on VOLUME 8, 2020 This work  ... 
doi:10.1109/access.2020.3006051 fatcat:p4ajpipfsvfoxal2tsmqamboci

REDUCING BIAS IN THE PROBABILISTIC EVALUATION OF AUDIO MUSIC SIMILARITY

Adriana María Suárez Iguarán, Julián Urbano, Emilia Gómez
2020 Zenodo  
Therefore, by doing better estimations of relevance judgments and using all the tools at hand (research, literature, technology) the time used by people performing this task can be utilized in others activities  ...  This thesis work conduits research toward the estimation of relevance judgments for the task of Audio Music Similarity in the context of MIREX.  ...  The organization of the first International Symposium on Music Information Retrieval (ISMIR) in 2000, with the intention of bringing together the MIR research community into one location to treat among  ... 
doi:10.5281/zenodo.3727056 fatcat:und4f7vaajaj5nyuqyleci2ad4

Confidence Intervals for Nonparametric Empirical Bayes Analysis [article]

Nikolaos Ignatiadis, Stefan Wager
2021 arXiv   pre-print
In this paper, we develop flexible and practical confidence intervals that provide asymptotic frequentist coverage of empirical Bayes estimands, such as the posterior mean or the local false sign rate.  ...  In an empirical Bayes analysis, we use data from repeated sampling to imitate inferences made by an oracle Bayesian with extensive knowledge of the data-generating distribution.  ...  Acknowledgments This paper was first presented on May 24th, 2018 at a workshop in honor of Bradley Efron's 80th birthday.  ... 
arXiv:1902.02774v4 fatcat:tjcu3sgx6nei3ecxvfeg3thxuq

ECIR 2020 Workshops: Assessing the Impact of Going Online [article]

Sérgio Nunes, Suzanne Little, Sumit Bhatia, Ludovico Boratto, Guillaume Cabanac, Ricardo Campos, Francisco M. Couto, Stefano Faralli, Ingo Frommholz, Adam Jatowt, Alípio Jorge, Mirko Marras (+2 others)
2020 arXiv   pre-print
In this report, we describe the experience of organizing the ECIR 2020 Workshops in this scenario from two perspectives: the workshop organizers and the workshop participants.  ...  We provide a report on the organizational aspect of these events and the consequences for participants. Covering the scientific dimension of each workshop is outside the scope of this article.  ...  BIAS 2020 [2] was the 1st edition of the International Workshop on Algorithmic Bias in Search and Recommendation 2 .  ... 
arXiv:2005.06748v1 fatcat:ktlzw4a25jdx3c2yajopw4uxhu

Toward User-Driven Algorithm Auditing: Investigating users' strategies for uncovering harmful algorithmic behavior

Alicia DeVos, Aditi Dhabalia, Hong Shen, Kenneth Holstein, Motahhare Eslami
2022 CHI Conference on Human Factors in Computing Systems  
Based on our findings, we present a process model capturing the dynamics of and influences on users' search and sensemaking behaviors.  ...  To investigate, we conducted a series of think-aloud interviews, diary studies, and workshops, exploring how users find and make sense of harmful behaviors in algorithmic systems, both individually and  ...  ACKNOWLEDGMENTS This work was supported by the National Science Foundation (NSF) program on Fairness in AI in collaboration with Amazon under Award No.  ... 
doi:10.1145/3491102.3517441 fatcat:obypclcgqzfwjjnst5rwgs24z4

Recommendations for the conduct of systematic reviews in toxicology and environmental health research (COSTER)

Paul Whaley, Elisa Aiassa, Claire Beausoleil, Anna Beronius, Gary Bilotta, Alan Boobis, Rob de Vries, Annika Hanberg, Sebastian Hoffmann, Neil Hunt, Carol F. Kwiatkowski, Juleen Lam (+9 others)
2020 Environment International  
To develop an expert, cross-sector consensus view on a key set of recommended practices for the planning and conduct of SRs in the environmental health sciences.  ...  A draft set of recommendations was derived from two existing standards for SRs in biomedicine and developed in a consensus process, which engaged international participation from government, industry,  ...  TW did not participate in the workshop but contributed to the consensus development calls and the manuscript.  ... 
doi:10.1016/j.envint.2020.105926 pmid:32653802 fatcat:4hd6p5r7uva5ngkwpkmrpkxomi

Recommendations for the conduct of systematic reviews in toxicology and environmental health research (COSTER)

Paul Whaley, Elisa Aiassa, Claire Beausoleil, Anna Beronius, Gary Bilotta, Alan Boobis, Rob de Vries, Annika Hanberg, Sebastian Hoffmann, Neil Hunt, Carol Kwiatkowski, Juleen Lam (+9 others)
2020 Zenodo  
Objectives: To develop an expert, cross-sector consensus view on a key set of recommended practices for the planning and conduct of SRs in the environmental health sciences.  ...  Methods: A draft set of recommendations was derived from two existing standards for SRs in biomedicine and developed in a consensus process, which engaged international participation from government, industry  ...  Acknowledgements We would like to thank Kate Jones and the Royal Society of Chemistry for hosting the workshop, and Lancaster University Faculty of Science and Technology and Lancaster Environment Centre  ... 
doi:10.5281/zenodo.3903115 fatcat:n3xf33nc3jfuvan4fh3v6h3hhe

The HINTS examination and STANDING algorithm in acute vestibular syndrome: A systematic review and meta-analysis involving frontline point-of-care emergency physicians

Millie Nakatsuka, Emma E. Molloy, Diego Kaski
2022 PLoS ONE  
Two further studies were identified by a manual search of references and an electronic search for any missed studies associated with the authors.  ...  Five studies were included in the qualitative synthesis. For the STANDING algorithm, there were two studies of 450 patients who were examined by 11 emergency physicians.  ...  Mark Paine (neuro-otology and neuro-ophthalmology specialist), Syeda Azim (statistician), and the team of librarians and translators.  ... 
doi:10.1371/journal.pone.0266252 pmid:35511910 pmcid:PMC9070939 fatcat:ilrbz4yt7bbibn67hwogyv6g5i

Dental Caries Diagnosis and Detection Using Neural Networks: A Systematic Review

María Prados-Privado, Javier García Villalón, Carlos Hugo Martínez-Martínez, Carlos Ivorra, Juan Carlos Prados-Frutos
2020 Journal of Clinical Medicine  
A search was conducted in PubMed, Institute of Electrical and Electronics Engineers (IEEE) Xplore, and ScienceDirect. Data extraction was performed independently by two reviewers.  ...  This systematic review aims to identify the state of the art of neural networks in caries detection and diagnosis.  ...  Med. 2020, 9, 3579  ... 
doi:10.3390/jcm9113579 pmid:33172056 fatcat:s2unb36ngrbn5a7hkuxloybuzu

An algorithm provided as initial guidance for reporting registry records and published protocols in systematic reviews

Julia Bidonde, Jose F. Meneses-Echavez, Angela J. Busch, Catherine Boden
2020 Journal of Clinical Epidemiology  
We hope that the algorithm generates further discussion to enhance the transparency of TRR/PP reporting and methodological research into the complexities of using protocols in systematic reviews of interventions  ...  Based on these elements, and our initial research, we created an algorithm/graphical aid to visualize initial direction.  ...  Acknowledgments Dr Jelena Savovic (University of Bristol) contributed to the preliminary results presented in South Africa Global Evidence Submit and provided feedback on original draft of this manuscript  ... 
doi:10.1016/j.jclinepi.2020.09.025 pmid:33002639 fatcat:4bjpuv247jbbrg2bvyipt5uoj4

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation [article]

Mathias Müller, Rico Sennrich
2021 arXiv   pre-print
In this paper, we empirically investigate the properties of MBR decoding on a number of previously reported biases and failure cases of beam search.  ...  Recent work has tied these shortcomings to beam search -- the de facto standard inference algorithm in NMT -- and Eikema & Aziz (2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples  ...  Acknowledgements This work has received funding from the Swiss National Science Foundation (grant numbers 105212-169888 and 176727).  ... 
arXiv:2105.08504v1 fatcat:penictuu65fpdc7gkrq3asqjne

Societal Biases in Language Generation: Progress and Challenges [article]

Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, Nanyun Peng
2021 arXiv   pre-print
To better understand these challenges, we present a survey on societal biases in language generation, focusing on how data and techniques contribute to biases and progress towards reducing biases.  ...  Language generation presents unique challenges for biases in terms of direct user interaction and the structure of decoding techniques.  ...  Acknowledgments We would like to thank Seraphina Goldfarb-Tarrant, Sunipa Dev, Jason Teoh, members of the Plus Lab, and our anonymous reviewers for the many helpful suggestions that went into this paper  ... 
arXiv:2105.04054v3 fatcat:dhwma4hvfbf7jke3lt227qb73i

Mitigating Bias in Algorithmic Systems – A Fish-Eye View [article]

Kalia Orphanou, Jahna Otterbacher, Styliani Kleanthous, Khuyagbaatar Batsuren, Fausto Giunchiglia, Veronika Bogina, Avital Shulner Tal, AlanHartman, Tsvi Kuflik
2022 arXiv   pre-print
Mitigating bias in algorithmic systems is a critical issue drawing attention across communities within the information and computer sciences.  ...  Given the complexity of the problem and the involvement of multiple stakeholders -- including developers, end-users, and third parties -- there is a need to understand the landscape of the sources of bias  ...  Acknowledgement This project is partially funded by the European Union's Horizon 2020 research and innovation programme under grant agreement No. 810105 (CyCAT).  ... 
arXiv:2103.16953v2 fatcat:b27zb3zusnfmzcspyl2njbivkq
« Previous Showing results 1 — 15 out of 4,802 results