paper-with-me

Papers

Semi-supervised Structured Prediction with Neural CRF Autoencoder

2017-09-01 · EMNLP 2017 9 · Xiao Zhang, Yong Jiang, Hao Peng, Kewei Tu, Dan Goldwasser

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.

📄 PDF Abstract BibTeX

Code (1)

cosmozhang/NCRF-AE 공식 구현

Tasks

DecoderPart-Of-Speech TaggingPOSPOS TaggingPredictionStructured Prediction

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음
CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

Similar Papers 제목 키워드 기반

Learning to Make Predictions on Graphs with Autoencoders

2018-02-23 · Phi Vu Tran

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+4

Multi-Task Graph Autoencoders

2018-11-07 · Phi Vu Tran

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+3

Semi-supervised Learning with the EM Algorithm: A Comparative Study between Unstructured and Structured Prediction

2020-08-28 · Wenchong He, Zhe Jiang

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 Prediction

Semi-Supervised Semantic Dependency Parsing Using CRF Autoencoders

2020-07-01 · ACL 2020 6 · Zixia Jia, Youmi Ma, Jiong Cai, Kewei Tu

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+1

Semi-Supervised Variational Autoencoder for Survival Prediction

2019-10-10 · Sveinn Pálsson, Stefano Cerri, Andrea Dittadi, Koen van Leemput

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