Sequence-to-sequence neural network models for transliteration

Published in

arXiv.org(2016)

External Links:

Generate Graph

TL;DR

It is demonstrated that neural sequence-to-sequence models obtain state of the art or close to state-of-the- art results on existing datasets.

Abstract

Transliteration is a key component of machine translation systems and software internationalization. This paper demonstrates that neural sequence-to-sequence models obtain state of the art or close to state of the art results on existing datasets. In an effort to make machine transliteration accessible, we open source a new Arabic to English transliteration dataset and our trained models.

Authors

T. Breuel

2 papers

Mihaela Rosca

1 papers

References17 items

Adaptive Computation Time for Recurrent Neural Networks

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Sequence-to-sequence neural net models for grapheme-to-phoneme conversion

Grapheme-to-phoneme conversion using Long Short-Term Memory recurrent neural networks

Sequence to Sequence Learning with Neural Networks

Sequence-to-sequence neural network models for transliteration

Published in

arXiv.org(2016)

External Links:

Generate Graph

TL;DR

It is demonstrated that neural sequence-to-sequence models obtain state of the art or close to state-of-the- art results on existing datasets.

Abstract

Authors

T. Breuel

2 papers

Mihaela Rosca

1 papers

References17 items

Adaptive Computation Time for Recurrent Neural Networks

TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Sequence-to-sequence neural net models for grapheme-to-phoneme conversion

Grapheme-to-phoneme conversion using Long Short-Term Memory recurrent neural networks

Sequence to Sequence Learning with Neural Networks

Neural Machine Translation by Jointly Learning to Align and Translate

Electro-cortical manifestations of common vs. proper name processing during reading

Normalizing historical orthography for OCR historical documents using LSTM

On the difficulty of training recurrent neural networks

Transliteration by Sequence Labeling with Lattice Encodings and Reranking

Named Entity Transcription with Pair n-Gram Models

A Deep Learning Approach to Machine Transliteration

A Sequence Alignment Model Based on the Averaged Perceptron

Listen, attend and spell

Phrase-based Machine Transliteration

Statistical Transliteration for Cross Language Information Retrieval using HMM alignment model and CRF

Connectionist Temporal Classiﬁcation: Labelling Unsegmented Sequence Data with Recurrent Neural Networks

Field of Study

Computer Science

Journal Information

Name

ArXiv

Volume

abs/2005.00687

Venue Information

Name

arXiv.org

Type

URL

https://arxiv.org

Alternate Names

ArXiv