A Multitask-Based Neural Machine Translation Model with Part-of-Speech Tags Integration for Arabic Dialects

The statistical machine translation for the Arabic language integrates external linguistic resources such as part-of-speech tags. The current research presents a Bidirectional Long Short-Term Memory (Bi-LSTM)—Conditional Random Fields (CRF) segment-level Arabic Dialect POS tagger model, which will b...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2018-12, Vol.8 (12), p.2502
Main Authors: Baniata, Laith H., Park, Seyoung, Park, Seong-Bae
Format: Article
Language:English
Subjects:
Accuracy
Arabic dialects
Arabic language
Berber languages
Bi-LSTM
Computer science
Conditional random fields
CRF
decoder
Decoders
Dialects
encoder
English language
French language
Intelligibility
Invariants
Italian language
Language
Languages
Latin language
Linguistics
Machine translation
Morphology
MSA
MTL
Multilingualism
Neural networks
Niger-Congo languages
NMT
Peptides
POS tagging
Principal components analysis
Romance languages
Spanish language
Speech
Standard dialects
Tagging (Computational linguistics)
Translation
Turkish language
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The statistical machine translation for the Arabic language integrates external linguistic resources such as part-of-speech tags. The current research presents a Bidirectional Long Short-Term Memory (Bi-LSTM)—Conditional Random Fields (CRF) segment-level Arabic Dialect POS tagger model, which will be integrated into the Multitask Neural Machine Translation (NMT) model. The proposed solution for NMT is based on the recurrent neural network encoder-decoder NMT model that has been introduced recently. The study has proposed and developed a unified Multitask NMT model that shares an encoder between the two tasks; Arabic Dialect (AD) to Modern Standard Arabic (MSA) translation task and the segment-level POS tagging tasks. A shared layer and an invariant layer are shared between the translation tasks. By training translation tasks and POS tagging task alternately, the proposed model can leverage the characteristic information and improve the translation quality from Arabic dialects to Modern Standard Arabic. The experiments are conducted from Levantine Arabic (LA) to MSA and Maghrebi Arabic (MA) to MSA translation tasks. As an additional linguistic resource, the segment-level part-of-speech tags for Arabic dialects were also exploited. Experiments suggest that translation quality and the performance of POS tagger were improved with the implementation of multitask learning approach.
ISSN:2076-3417
2076-3417
DOI:10.3390/app8122502