Insiders Hub

Neural Machine Translation using Seq2Seq with Attention

Pranab Sarkar

Pranab Sarkar

Jalpaiguri, West Bengal

7 0

Machine translation is the task of automatically converting source text in one language to text in another language. According to research firm Common Sense Advisory, 72.1 percent of the consumers spend most or all of their time on sites in their own language, 72.4 percent say they would be more likely to buy a product with information in their own language and 56.2 percent say that the ability to obtain information in their own language is more important than price. These are just a few of the many reasons that translation has become essential in the modern and ever more globalized world that we live in. Machine translation is a tool that can help businesses and individuals in many ways. While machine translation is unlikely to totally replace human beings in any application where quality is really important, there are a growing number of cases that show how effective and useful machine translation can be. Neural machine translation (NMT) is an approach to machine translation that uses a large artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model. Here, I have created an model which translates a given English sentence to German using a tensorflow which can be used using a web UI. ...learn more

Project status: Published/In Market

Artificial Intelligence, Graphics and Media

Groups
Early Innovation for PC Skills

Intel Technologies
Intel Opt ML/DL Framework

Code Samples [1]

Overview / Usage

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems.

Why seq2seq ?
Sequence-to-Sequence (seq2seq) models are used for a variety of NLP tasks, such as text summarization, speech recognition, DNA sequence modeling, among others. Our aim is to translate given sentences from one language to another.

Need of Machine Translation?

  1. There is great business value in enabling new and existing content to be translated. When customized, machine translation provides greater efficiency and productivity, lowering costs and increasing Return On Investment (ROI).

  2. Real-time communications where it would not be practical for a human to translate (e.g. chat and email.)

  3. Speech-recognition systems. E.g.- Amazon Alexa, Google Assistant, Google Duplex.

How will we measure the quality of translation?
BLEU, or the Bilingual Evaluation Understudy, is a score for comparing a candidate translation of text to one or more reference translations.

Methodology / Approach

Data: http://www.manythings.org/anki/deu-eng.zip

Steps followed to train the model:

  1. Read the Dataset.
  2. Text Pre-Processing.
  3. Text to Sequence Conversion.
  4. Model Building(Input->Embreddings->Encoder->Decoder->Dense->Output)
  5. Deployment in a flask web app.

Technologies Used

Tensorflow
Python
Flask

Repository

https://github.com/pranabsarkar/English-to-German-Translator-using-seq2seq-model

Collaborators

There are no people to show.

Comments (0)