A Deep Learning Approach to Machine Transliteration

By Thomas Deselaers, Sasa Hasan, Oliver Bender, Hermann Ney. 2009

135 citations recorded by the source corpus.

In this paper we present a novel transliteration technique which is based on deep belief networks. Common approaches use finite state machines or other methods similar to conventional machine translation. Instead of using conventional NLP techniques, the approach presented here builds on deep belief networks, a technique which was shown to work well for other machine learning problems. We show that deep belief networks have certain properties which are very interesting for transliteration and possibly also for translation and that a combination with conventional techniques leads to an improvement over both components on an Arabic-English transliteration task.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Learning: Methods and Applications (2014, methodology): “An earlier study on applying deep learning techniques with DBNs was provided in [111] to attack a machine transliteration problem, a much easier task than machine translation.”
Deep Belief Networks for phone recognition (2009, methodology): “DBNs and related models have been used successfully for hand -written character recognition [14, 15], 3-D object recognition [16], information retrieval [1 7, 18], motion capture data modeling [19, 20], and machine transliteration [21].”
An Overview of Deep-Structured Learning for Information Processing (2011, methodology): “A similar multi-task learning technique with DBN is used in (Deselaers et al., 2009) to attack a machine transliteration problem, which may be generalized to a more difficult machine translation problem.”
IXA Biomedical Translation System at WMT16 Biomedical Translation Task (2016, methodology): “State-of-the-art shows many approaches for transliteration in machine translation, most of them based on statistical methods (Deselaers et al., 2009; Habash, 2008; Hermjakob et al., 2008; Rama and Gali, 2009).”
Deep Learning and Its Applications to Signal and Information Processing (2011, methodology): “A similar multitask learning technique with DBN is used in [ 3 ] to attack the machine transliteration problem, which may be generalized to the more difficult problem of machine translation.,[ 3 ] L. Chiariglione, “The digital media manifestovision” [Online].”
Optimizing Neural Networks that Generate Iimages (2014, methodology): “Many papers have used this strategy: (Hinton et al., 2006; Salakhutdinov & Hinton, 2009a; Lee et al., 2009; Nair & Hinton, 2010a; Salakhutdinov & Hinton, 2009b; Hinton & Salakhutdinov, 2006; Deselaers et al., 2009; Mohamed et al., 2012), to name just a few.”
Acoustic Modeling Using Deep Belief Networks (2012, methodology): “This type of generative pre-training followed by discriminative fine-tuning has been used successfully for hand-writ ten character recognition [11], [10], [19], dimensionality re duction [20], 3-D object recognition [21], [22], extracting road ma ps from cluttered aerial images [23], information ret”
A Survey of the Usages of Deep Learning for Natural Language Processing (2020, unknown): “as proper nouns, into different languages [241].”
Hierarchical Convolutional Neural Networks for EEG-Based Emotion Recognition (2017, background): “deep learning (DL) has dominated the machine learning field and showed advantage in some complex tasks [31, 32].”
Voice conversion in high-order eigen space using deep belief nets (2013, methodology): “DBNs and related models have been used, for example, for hand-written character recognition [21], 3-D object recognition [22], machine transliteration [23], and speech recognition tasks [24].”
Named Entity Recognition in Chinese Clinical Text Using Deep Neural Network (2015, background): “It has achieved state-of-the-art performances in a number of different applications across multiple domains, such as image processing [27], automatic speech recognition [28] and machine translation [29].”
Roles of Pre-Training and Fine-Tuning in Context-Dependent DBN-HMMs for Real-World Speech Recognition (2010, methodology): “Deep learning techniques have been successfully applied to applications such as natural language processing [12][13], language recognition [14], image processing [15], vision [16], audio encoding [17], audio classification [18], phone recognition [19], and semantic tagging [20] in the last several y”