Arabic Machine Transliteration using an Attention-based Encoder-decoder Model

被引：19

作者：

Ameur, Mohamed Seghir Hadj ^{[1
]}

Meziane, Farid ^{[2
]}

Guessoum, Ahmed ^{[1
]}

机构：

[1] USTHB Univ, TALAA Grp, Algiers, Algeria

[2] Univ Salford, Informat Res Ctr, Salford M5 4WT, Lancs, England

来源：

ARABIC COMPUTATIONAL LINGUISTICS (ACLING 2017) | 2017年 / 117卷

关键词：

Natural Language Processing; Arabic Language; Arabic Transliteration; Deep Learning; Sequence-to-sequence Models; Encoder-decoder Architecture; Recurrent Neural Networks;

D O I：

10.1016/j.procs.2017.10.120

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Transliteration is the process of converting words from a given source language alphabet to a target language alphabet, in a way that best preserves the phonetic and orthographic aspects of the transliterated words. Even though an important effort has been made towards improving this process for many languages such as English, French and Chinese, little research work has been accomplished with regard to the Arabic language. In this work, an attention-based encoder-decoder system is proposed for the task of Machine Transliteration between the Arabic and English languages. Our experiments proved the efficiency of our proposal approach in comparison to some previous research developed in this area. (C) 2017 The Authors. Published by Elsevier B.V.

引用

页码：287 / 297

页数：11

共 31 条

[1]

AbdulJaleel N., ENGLISH ARABIC TRANS

[2]

[Anonymous], 1990, COMPUT LINGUIST

[3]

[Anonymous], 2014, Advances in neural information processing systems

[4]

[Anonymous], ARXIV14061078

[5]

[Anonymous], 1997, Neural Computation

[6]

[Anonymous], 2016, P 6 NAMED ENTITY WOR

[7]

[Anonymous], 2010, Statistical Machine Translation

[8]

[Anonymous], 2009, Proceedings of the 4th Workshop on Statistical Machine Translation

[9]

[Anonymous], 6 NAM ENT WORKSH JOI

[10]

[Anonymous], 2005, P 43 ANN M ASS COMP

← 1 2 3 4 →