A Multitask-Based Neural Machine Translation Model with Part-of-Speech Tags Integration for Arabic Dialects
School of Computer Science and Engineering, Kyungpook National University, 80 Daehakro, Buk-gu, Daegu 41566, Korea
Department of Computer Science and Engineering, Kyung Hee University, 1732 Deogyeong-daero, Giheung-gu, Yongin 17104, Korea
Author to whom correspondence should be addressed.
Appl. Sci. 2018, 8(12), 2502; https://doi.org/10.3390/app8122502
Received: 29 October 2018 / Revised: 29 November 2018 / Accepted: 1 December 2018 / Published: 5 December 2018
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.