Git Product home page Git Product logo

baosongyang / wat17 Goto Github PK

View Code? Open in Web Editor NEW

This project forked from nem6ishi/wat17

0.0 1.0 0.0 425 KB

This is the official code used for WAT 2017 Description Paper titled A Bag of Useful Tricks for Practical Neural Machine Translation: Embedding Layer Initialization and Large Batch Size.

License: Apache License 2.0

Shell 4.35% Python 93.42% CSS 0.18% JavaScript 0.93% Perl 1.11%

wat17's Introduction

WAT 2017: UT-IIS

This is the official code used for WAT 2017 Description Paper titled A Bag of Useful Tricks for Practical Neural Machine Translation: Embedding Layer Initialization and Large Batch Size.

This program is based on Google's seq2seq implementation.

You may read the documentation of the original implementation at https://google.github.io/seq2seq/.

Added Features

The following two features are added to the original implementation.

  1. Embedding Layer Initialization
  2. Ensemble of models

The example usage of our code are in ./examples directory.

Preparing Word Embedding File

To create word embedding, please refer to ./data_preparation/init_vocab_w2v.sh. This script train word embeddings and convert them into .npy format.

Reference

@InProceedings{neishi:WAT2017,
  author    = {Neishi, Masato  and  Sakuma, Jin  and  Tohda, Satoshi  and  Ishiwatari, Shonosuke and Yoshinaga, Naoki and Toyoda, Masashi},
  title     = {A Bag of Useful Tricks for Practical Neural Machine Translation: Embedding Layer Initialization and Large Batch Size},
  booktitle = {Proceedings of the 4rd Workshop on Asian Translation (WAT2017)},
  year      = {2017 (to appear)}
}

The citation for Google's original paper.

@ARTICLE{Britz:2017,
  author          = {{Britz}, Denny and {Goldie}, Anna and {Luong}, Thang and {Le}, Quoc},
  title           = "{Massive Exploration of Neural Machine Translation Architectures}",
  journal         = {ArXiv e-prints},
  archivePrefix   = "arXiv",
  eprinttype      = {arxiv},
  eprint          = {1703.03906},
  primaryClass    = "cs.CL",
  keywords        = {Computer Science - Computation and Language},
  year            = 2017,
  month           = mar,
}

wat17's People

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.