Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machine Translation

Citations Over TimeTop 10% of 2014 papers

Abstract

In this paper, instead of designing new features based on intuition, linguistic knowledge and domain, we learn some new and effective features using the deep autoencoder (DAE) paradigm for phrase-based translation model. Using the unsupervised pre-trained deep belief net (DBN) to initialize DAE's parameters and using the input original phrase features as a teacher for semi-supervised fine-tuning, we learn new semi-supervised DAE features, which are more effective and stable than the unsupervised DBN features. Moreover, to learn high dimensional feature representation, we introduce a natural horizontal composition of more DAEs for large hidden layers feature learning. On two Chinese-English tasks, our semi-supervised DAE features obtain statistically significant improvements of 1.34/2.45 (IWSLT) and 0.82/1.52 (NIST) BLEU points over the unsupervised DBN features and the baseline features, respectively.

Related Papers

• → Optimization Strategy of a Stacked Autoencoder and Deep Belief Network in a Hyperspectral Remote-Sensing Image Classification Model(2023)7 cited
• → Representation Learning: Recommendation With Knowledge Graph via Triple-Autoencoder(2022)6 cited
• → Self-taught Learning with Residual Sparse Autoencoders for HEp-2 Cell Staining Pattern Recognition(2018)1 cited
• → Residual Sparse Autoencoders for Unsupervised Feature Learning and Its Application to HEp-2 Cell Staining Pattern Recognition(2019)1 cited