Literature Survey: Study of Neural Machine Translation

نویسندگان

  • Jigar Mistry
  • Ajay Anand Verma
  • Pushpak Bhattacharyya
چکیده

We build Neural Machine Translation (NMT) systems for EnglishHindi,Bengali-Hindi and Gujarati-Hindi with two different units of translation i.e. word and subword and present a comparative study of subword NMT and word level NMT systems, along with strong results and case studies. We train attention-based encoder-decoder model for word level and use Byte Pair Encoding (BPE) in subword NMT for word segmentation. We conduct case studies to study the effects of BPE. Since the NMT approach is a data driven approach, it suffers a lot by resource scarcity. This report also covers the Multitask learning which is an approach of transfer learning or inductive transfer. MultiTask Learning helps the learner to improve generalization performance by adding extra related tasks to the backpropagation net. The nub behind adding extra related tasks is domain specific information contained in the training signals of other tasks helps to learn shared feature of the main task better. We explained Multiway multilingual model which is based on the MTL approach which learns the translation of several Indian language pairs in parallel. We also covers the performance gained by Multi-way multilingual neural machine translation in contrast with single pair neural machine translation.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Comparative Study of English-Persian Translation of Neural Google Translation

Many studies abroad have focused on neural machine translation and almost all concluded that this method was much closer to humanistic translation than machine translation. Therefore, this paper aimed at investigating whether neural machine translation was more acceptable in English-Persian translation in comparison with machine translation. Hence, two types of text were chosen to be translated...

متن کامل

The Correlation of Machine Translation Evaluation Metrics with Human Judgement on Persian Language

Machine Translation Evaluation Metrics (MTEMs) are the central core of Machine Translation (MT) engines as they are developed based on frequent evaluation. Although MTEMs are widespread today, their validity and quality for many languages is still under question. The aim of this research study was to examine the validity and assess the quality of MTEMs from Lexical Similarity set on machine tra...

متن کامل

Protein Secondary Structure Prediction: a Literature Review with Focus on Machine Learning Approaches

DNA sequence, containing all genetic traits is not a functional entity. Instead, it transfers to protein sequences by transcription and translation processes. This protein sequence takes on a 3D structure later, which is a functional unit and can manage biological interactions using the information encoded in DNA. Every life process one can figure is undertaken by proteins with specific functio...

متن کامل

Reordering Models for Statistical Machine Translation: A Literature Survey

In this survey, we briefly study various reordering models that are used with statistical translation models. Reordering model is one of the important component of any statistical machine translation system. Problem of reordering is NP-Hard itself. In this survey, we study various reordering approaches that can be used to solve this problem. We first study simple distortion-based reordering whi...

متن کامل

Literature Survey: Neural Machine Translation

Neural Machine Translation (NMT) is a new highly active approach for machine translation, which has showed promising results and due to its success it has attracted many researchers in the field. In this paper we investigate how NMT architecture changed over very short span of time. Starting with basic encoder-decoder architecture that suffered two problems, poor performance with longer sentenc...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017