Regularized Minimax Conditional Entropy for Crowdsourcing

There is a rapidly increasing interest in crowdsourcing for data labeling. By crowdsourcing, a large number of labels can be often quickly gathered at low cost. However, the labels provided by the crowdsourcing workers are usually not of high quality. In this paper, we propose a minimax conditional entropy principle to infer ground truth from noisy crowdsourced labels. Under this principle, we derive a unique probabilistic labeling model jointly parameterized by worker ability and item difficulty. We also propose an objective measurement principle, and show that our method is the only method which satisfies this objective measurement principle. We validate our method through a variety of real crowdsourcing datasets with binary, multiclass or ordinal labels.

[1]  Qiang Liu,et al.  Aggregating Ordinal Labels from Crowds by Minimax Conditional Entropy , 2014, ICML.

[2]  John C. Platt,et al.  Learning from the Wisdom of Crowds by Minimax Entropy , 2012, NIPS.

[3]  Tom Minka,et al.  How To Grade a Test Without Knowing the Answers - A Bayesian Graphical Model for Adaptive Crowdsourcing and Aptitude Testing , 2012, ICML.

[4]  Xi Chen,et al.  Optimistic Knowledge Gradient Policy for Optimal Budget Allocation in Crowdsourcing , 2013, ICML.

[5]  Pietro Perona,et al.  The Multidimensional Wisdom of Crowds , 2010, NIPS.

[6]  Song-Chun Zhu,et al.  Minimax Entropy Principle and Its Application to Texture Modeling , 1997, Neural Computation.

[7]  Brendan T. O'Connor,et al.  Cheap and Fast – But is it Good? Evaluating Non-Expert Annotations for Natural Language Tasks , 2008, EMNLP.

[8]  Peng Dai,et al.  POMDP-based control of workflows for crowdsourcing , 2013, Artif. Intell..

[9]  Jian Peng,et al.  Variational Inference for Crowdsourcing , 2012, NIPS.

[10]  D. Andrich A rating formulation for ordered response categories , 1978 .

[11]  Aleksandrs Slivkins,et al.  Adaptive Contract Design for Crowdsourcing Markets: Bandit Algorithms for Repeated Principal-Agent Problems , 2016, J. Artif. Intell. Res..

[12]  W. Grove,et al.  A latent trait finite mixture model for the analysis of rating agreement. , 1993, Biometrics.

[13]  Geoffrey E. Hinton,et al.  A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants , 1998, Learning in Graphical Models.

[14]  G. Rasch,et al.  A MATHEMATICAL THEORY OF OBJECTIVITY AND ITS CONSEQUENCES FOR MODEL CONSTRUCTION , 1968 .

[15]  David Baker,et al.  Algorithm discovery by protein folding game players , 2011, Proceedings of the National Academy of Sciences.

[16]  Xiaoming Liu,et al.  Demographic Estimation from Face Images: Human vs. Machine Performance , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Anirban Dasgupta,et al.  Aggregating crowdsourced binary ratings , 2013, WWW.

[18]  Walter S. Lasecki,et al.  Adaptive time windows for real-time crowd captioning , 2013, CHI Extended Abstracts.

[19]  R. Preston McAfee,et al.  Who moderates the moderators?: crowdsourcing abuse detection in user-generated content , 2011, EC '11.

[20]  Panagiotis G. Ipeirotis,et al.  Get another label? improving data quality and data mining using multiple, noisy labelers , 2008, KDD.

[21]  Gagan Goel,et al.  Mechanism Design for Crowdsourcing: An Optimal 1-1/e Competitive Budget-Feasible Mechanism for Large Markets , 2014, 2014 IEEE 55th Annual Symposium on Foundations of Computer Science.

[22]  Yurii Nesterov,et al.  Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.

[23]  Jun'ichi Tsujii,et al.  Evaluation and Extension of Maximum Entropy Models with Inequality Constraints , 2003, EMNLP.

[24]  Anima Anandkumar,et al.  Tensor decompositions for learning latent variable models , 2012, J. Mach. Learn. Res..

[25]  Ronald Rosenfeld,et al.  A survey of smoothing techniques for ME models , 2000, IEEE Trans. Speech Audio Process..

[26]  Daphne Koller,et al.  Hierarchically Classifying Documents Using Very Few Words , 1997, ICML.

[27]  A. P. Dawid,et al.  Maximum Likelihood Estimation of Observer Error‐Rates Using the EM Algorithm , 1979 .

[28]  Milad Shokouhi,et al.  Community-based bayesian aggregation models for crowdsourcing , 2014, WWW.

[29]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[30]  John D. Lafferty,et al.  Boosting and Maximum Likelihood for Exponential Models , 2001, NIPS.

[31]  G. Masters A rasch model for partial credit scoring , 1982 .

[32]  G. Rasch On General Laws and the Meaning of Measurement in Psychology , 1961 .

[33]  M. R. Novick,et al.  Statistical Theories of Mental Test Scores. , 1971 .

[34]  Devavrat Shah,et al.  Budget-Optimal Task Allocation for Reliable Crowdsourcing Systems , 2011, Oper. Res..

[35]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[36]  Yuandong Tian,et al.  Learning from crowds in the presence of schools of thought , 2012, KDD.

[37]  Gerardo Hermosillo,et al.  Learning From Crowds , 2010, J. Mach. Learn. Res..

[38]  Alexander J. Smola,et al.  Unifying Divergence Minimization and Statistical Inference Via Convex Duality , 2006, COLT.

[39]  Ittai Abraham,et al.  Adaptive Crowdsourcing Algorithms for the Bandit Survey Problem , 2013, COLT.

[40]  Xi Chen,et al.  Spectral Methods Meet EM: A Provably Optimal Algorithm for Crowdsourcing , 2014, J. Mach. Learn. Res..

[41]  Nihar B. Shah,et al.  Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing , 2014, J. Mach. Learn. Res..

[42]  Andreas Krause,et al.  Truthful incentives in crowdsourcing tasks using regret minimization mechanisms , 2013, WWW.

[43]  Javier R. Movellan,et al.  Whose Vote Should Count More: Optimal Integration of Labels from Labelers of Unknown Expertise , 2009, NIPS.

[44]  Chris Callison-Burch,et al.  Crowdsourcing Translation: Professional Quality from Non-Professionals , 2011, ACL.

[45]  Qiang Liu,et al.  Scoring Workers in Crowdsourcing: How Many Control Questions are Enough? , 2013, NIPS.

[46]  Miroslav Dudík,et al.  Maximum Entropy Density Estimation with Generalized Regularization and an Application to Species Distribution Modeling , 2007, J. Mach. Learn. Res..

[47]  Chao Gao,et al.  Minimax Optimal Convergence Rates for Estimating Ground Truth from Crowdsourced Labels , 2013, 1310.5764.