Neutron: An Implementation of the Transformer Translation Model and its Variants

Hongfei Xu, Qiuhui Liu
3/18/2019
cs.CL

No confident code implementation found for this paper.

Abstract

The Transformer translation model is easier to parallelize and provides better performance compared to recurrent seq2seq models, which makes it popular among industry and research community. We implement the Neutron in this work, including the Transformer model and its several variants from most recent researches. It is highly optimized, easy to modify and provides comparable performance with interesting features while keeping readability.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation

81% match1 repo2.9k2018

An Evaluation of Persian-English Machine Translation Datasets with Transformers

81% match2023

kNN-BOX: A Unified Framework for Nearest Neighbor Generation

79% match1 repo1042023

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

79% match1 repo5912023

A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization

78% match1 repo6462019

Glancing Future for Simultaneous Machine Translation

78% match1 repo32023

Cite this paper

@article{xu2019neutron,
  title  = {Neutron: An Implementation of the Transformer Translation Model and its Variants},
  author = {Hongfei Xu and Qiuhui Liu},
  year   = {2019},
  eprint = {1903.07402},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1903.07402}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1903.07402.svg)](https://codeofpaper.com/paper/1903.07402)

Discussion