%0 Generic %1 ratner2016programming %A Ratner, Alexander %A De Sa, Christopher %A Wu, Sen %A Selsam, Daniel %A Ré, Christopher %D 2016 %K data deep_learning %T Data Programming: Creating Large Training Sets, Quickly %U http://arxiv.org/abs/1605.07723 %X Large labeled training sets are the critical building blocks of supervised learning methods and are key enablers of deep learning techniques. For some applications, creating labeled training sets is the most time-consuming and expensive part of applying machine learning. We therefore propose a paradigm for the programmatic creation of training sets called data programming in which users provide a set of labeling functions, which are programs that heuristically label large subsets of data points, albeit noisily. By viewing these labeling functions as implicitly describing a generative model for this noise, we show that we can recover the parameters of this model to "denoise" the training set. Then, we show how to modify a discriminative loss function to make it noise-aware. We demonstrate our method over a range of discriminative models including logistic regression and LSTMs. We establish theoretically that we can recover the parameters of these generative models in a handful of settings. Experimentally, on the 2014 TAC-KBP relation extraction challenge, we show that data programming would have obtained a winning score, and also show that applying data programming to an LSTM model leads to a TAC-KBP score almost 6 F1 points over a supervised LSTM baseline (and into second place in the competition). Additionally, in initial user studies we observed that data programming may be an easier way to create machine learning models for non-experts.

@misc{ratner2016programming, abstract = {Large labeled training sets are the critical building blocks of supervised learning methods and are key enablers of deep learning techniques. For some applications, creating labeled training sets is the most time-consuming and expensive part of applying machine learning. We therefore propose a paradigm for the programmatic creation of training sets called data programming in which users provide a set of labeling functions, which are programs that heuristically label large subsets of data points, albeit noisily. By viewing these labeling functions as implicitly describing a generative model for this noise, we show that we can recover the parameters of this model to "denoise" the training set. Then, we show how to modify a discriminative loss function to make it noise-aware. We demonstrate our method over a range of discriminative models including logistic regression and LSTMs. We establish theoretically that we can recover the parameters of these generative models in a handful of settings. Experimentally, on the 2014 TAC-KBP relation extraction challenge, we show that data programming would have obtained a winning score, and also show that applying data programming to an LSTM model leads to a TAC-KBP score almost 6 F1 points over a supervised LSTM baseline (and into second place in the competition). Additionally, in initial user studies we observed that data programming may be an easier way to create machine learning models for non-experts.}, added-at = {2016-11-30T12:44:41.000+0100}, author = {Ratner, Alexander and De Sa, Christopher and Wu, Sen and Selsam, Daniel and Ré, Christopher}, biburl = {https://www.bibsonomy.org/bibtex/2fc3913524049786a7414f77134b5dff5/dallmann}, description = {Data Programming: Creating Large Training Sets, Quickly}, interhash = {57950bb971c095361d1baafb06bd543a}, intrahash = {fc3913524049786a7414f77134b5dff5}, keywords = {data deep_learning}, note = {cite arxiv:1605.07723}, timestamp = {2016-11-30T12:44:41.000+0100}, title = {Data Programming: Creating Large Training Sets, Quickly}, url = {http://arxiv.org/abs/1605.07723}, year = 2016 }