Semi-supervised Structured Prediction with Neural CRF Autoencoder
In this paper we propose an end-to-end neural CRF autoencoder (NCRF-AE) model for semi-supervised learning of sequential structured prediction problems. Our NCRF-AE consists of two parts: an encoder which is a CRF model enhanced by deep neural networks, and a decoder which is a generative model trying to reconstruct the input. Our model has a unified structure with different loss functions for labeled and unlabeled data with shared parameters. We developed a variation of the EM algorithm for optimizing both the encoder and the decoder simultaneously by decoupling their parameters. Our Experimental results over the Part-of-Speech (POS) tagging task on eight different languages, show that our model can outperform competitive systems in both supervised and semi-supervised scenarios.
Code (1)
Tasks
DecoderPart-Of-Speech TaggingPOSPOS TaggingPredictionStructured PredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning to Make Predictions on Graphs with Autoencoders
We examine two fundamental tasks associated with graph representation learning: link prediction and semi-supervised node classification. We present a novel autoencoder architecture capable of learning a joint representat…
ClassificationGeneral ClassificationGraph Representation LearningLink Prediction+4Multi-Task Graph Autoencoders
We examine two fundamental tasks associated with graph representation learning: link prediction and node classification. We present a new autoencoder architecture capable of learning a joint representation of local graph…
General ClassificationGraph EmbeddingGraph Representation LearningLink Prediction+3Semi-supervised Learning with the EM Algorithm: A Comparative Study between Unstructured and Structured Prediction
Semi-supervised learning aims to learn prediction models from both labeled and unlabeled samples. There has been extensive research in this area. Among existing work, generative mixture models with Expectation-Maximizati…
PredictionStructured PredictionSemi-Supervised Semantic Dependency Parsing Using CRF Autoencoders
Semantic dependency parsing, which aims to find rich bi-lexical relationships, allows words to have multiple dependency heads, resulting in graph-structured representations. We propose an approach to semi-supervised lear…
ARCDecoderDependency ParsingSemantic Dependency Parsing+1Semi-Supervised Variational Autoencoder for Survival Prediction
In this paper we propose a semi-supervised variational autoencoder for classification of overall survival groups from tumor segmentation masks. The model can use the output of any tumor segmentation algorithm, removing a…
Brain Tumor SegmentationPredictionSegmentationSurvival Analysis+2