Sequence-to-sequence neural network models for transliteration

2016/10/29 by Rosca, Mihaela, Breuel, Thomas · 1 citation
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1610.09565

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.

Cited by

• MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs

Related

• Neural Machine Transliteration: Preliminary Results
• Sequence to Sequence Networks for Roman-Urdu to Urdu Transliteration
• Urdu-English Machine Transliteration using Neural Networks
• Transliteration of Judeo-Arabic Texts into Arabic Script Using Recurrent\n Neural Networks
• English-to-Chinese Transliteration with Phonetic Back-transliteration