MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation
Machine translation (MT) is the automatic translation of the source language to its target language by a computer system. In the current paper, we propose an approach of using recurrent neural networks (RNNs) over traditional statistical MT (SMT). We compare the performance of the phrase table of SM...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2019-07-01
|
Series: | Journal of Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1515/jisys-2018-0016 |
id |
doaj-23a1c8f14bed4bb2a9026b8875d69b57 |
---|---|
record_format |
Article |
spelling |
doaj-23a1c8f14bed4bb2a9026b8875d69b572021-09-06T19:40:38ZengDe GruyterJournal of Intelligent Systems0334-18602191-026X2019-07-0128344745310.1515/jisys-2018-0016MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine TranslationMahata Sainik Kumar0Das Dipankar1Bandyopadhyay Sivaji2Computer Science and Engineering, Jadavpur University, Kolkata, West Bengal, IndiaComputer Science and Engineering, Jadavpur University, Kolkata, West Bengal, IndiaComputer Science and Engineering, Jadavpur University, Kolkata, West Bengal, IndiaMachine translation (MT) is the automatic translation of the source language to its target language by a computer system. In the current paper, we propose an approach of using recurrent neural networks (RNNs) over traditional statistical MT (SMT). We compare the performance of the phrase table of SMT to the performance of the proposed RNN and in turn improve the quality of the MT output. This work has been done as a part of the shared task problem provided by the MTIL2017. We have constructed the traditional MT model using Moses toolkit and have additionally enriched the language model using external data sets. Thereafter, we have ranked the phrase tables using an RNN encoder-decoder module created originally as a part of the GroundHog project of LISA lab.https://doi.org/10.1515/jisys-2018-0016machine translationrecurrent neural networkstatistical machine translationlanguage model |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mahata Sainik Kumar Das Dipankar Bandyopadhyay Sivaji |
spellingShingle |
Mahata Sainik Kumar Das Dipankar Bandyopadhyay Sivaji MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation Journal of Intelligent Systems machine translation recurrent neural network statistical machine translation language model |
author_facet |
Mahata Sainik Kumar Das Dipankar Bandyopadhyay Sivaji |
author_sort |
Mahata Sainik Kumar |
title |
MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation |
title_short |
MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation |
title_full |
MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation |
title_fullStr |
MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation |
title_full_unstemmed |
MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation |
title_sort |
mtil2017: machine translation using recurrent neural network on statistical machine translation |
publisher |
De Gruyter |
series |
Journal of Intelligent Systems |
issn |
0334-1860 2191-026X |
publishDate |
2019-07-01 |
description |
Machine translation (MT) is the automatic translation of the source language to its target language by a computer system. In the current paper, we propose an approach of using recurrent neural networks (RNNs) over traditional statistical MT (SMT). We compare the performance of the phrase table of SMT to the performance of the proposed RNN and in turn improve the quality of the MT output. This work has been done as a part of the shared task problem provided by the MTIL2017. We have constructed the traditional MT model using Moses toolkit and have additionally enriched the language model using external data sets. Thereafter, we have ranked the phrase tables using an RNN encoder-decoder module created originally as a part of the GroundHog project of LISA lab. |
topic |
machine translation recurrent neural network statistical machine translation language model |
url |
https://doi.org/10.1515/jisys-2018-0016 |
work_keys_str_mv |
AT mahatasainikkumar mtil2017machinetranslationusingrecurrentneuralnetworkonstatisticalmachinetranslation AT dasdipankar mtil2017machinetranslationusingrecurrentneuralnetworkonstatisticalmachinetranslation AT bandyopadhyaysivaji mtil2017machinetranslationusingrecurrentneuralnetworkonstatisticalmachinetranslation |
_version_ |
1717767987558088704 |