Unsupervised Deep Belief Features for Speech Translation
نویسندگان
چکیده
We present a novel formalism for introducing deep belief features to Hierarchical Machine Translation Model. The deep features are generated by unsupervised training of a deep belief network built with stacked sets of Restricted Boltzmann Machines. We show that our new deep feature based hierarchical model is better than the baseline hierarchical model with gains for two different languages pairs in two different data size settings. We obtain absolute BLEU score improvement of +1.13 on Darito-English and +0.66 on English-to-Dari Transtac Evaluation task. We also observe gains on English-to-Chinese translation task.
منابع مشابه
Learning New Semi-Supervised Deep Auto-encoder Features for Statistical Machine Translation
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-tunin...
متن کاملUnsupervised feature learning for audio classification using convolutional deep belief networks
In recent years, deep learning approaches have gained significant interest as a way of building hierarchical representations from unlabeled data. However, to our knowledge, these deep learning approaches have not been extensively studied for auditory data. In this paper, we apply convolutional deep belief networks to audio data and empirically evaluate them on various audio classification tasks...
متن کاملSpeech Recognition Using Deep Learning Algorithms
Automatic speech recognition, translating of spoken words into text, is still a challenging task due to the high viability in speech signals. Deep learning, sometimes referred as representation learning or unsupervised feature learning, is a new area of machine learning. Deep learning is becoming a mainstream technology for speech recognition and has successfully replaced Gaussian mixtures for ...
متن کاملDeep Learning with Nonparametric Clustering
Clustering is an essential problem in machine learning and data mining. One vital factor that impacts clustering performance is how to learn or design the data representation (or features). Fortunately, recent advances in deep learning can learn unsupervised features effectively, and have yielded state of the art performance in many classification problems, such as character recognition, object...
متن کاملKeyword Spotting with Convolutional Deep Belief Networks and Dynamic Time Warping
To spot keywords on handwritten documents, we present a hybrid keyword spotting system, based on features extracted with Convolutional Deep Belief Networks and using Dynamic Time Warping for word scoring. Features are learned from word images, in an unsupervised manner, using a sliding window to extract horizontal patches. For two single writer historical data sets, it is shown that the propose...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2012