Counting 2,870 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
Jun. 11, 2018
Sep. 2, 2017

Word Ordering: Can Neural Networks Put a Scramble of Words in Correct Order?

When learning a second language, one of the hardest challenges is likely to be familiar with the word order. Word order can be also important in machine translation because translation is, roughly speaking, a process that one arranges words of target language which are equivalent to source language in order. Probably you've done a word scramble game where you are to put shuffled words or letters in the original order. I think it's quite fun to see if neural networks can do it. Okay. Can you order the following words correctly?

can translation machine order also important be word in


  • NumPy >= 1.11.1
  • TensorFlow == 1.2 (Probably 1.3 should work, too, though I didn't test it)
  • matplotlib
  • distance
  • tqdm

Model Architecture

I employ the Transformer which was introduced in the paper Attention Is All You Need. It's known to the state-of-the-art model in the machine translation task as of 2017. However, I don't know if it fits in this task the best. Actually, I think a simpler architecture may work. The figure below is borrowed from the paper.

File description

  • includes all hyper parameters that are needed.
  • contains functions regarding loading and batching data.
  • has all building blocks for encoder/decoder networks.
  • contains the model and training code.
  • is for evaluation and inference.


Training Loss and Accuracy

  • Training Loss

  • Training Accuracy


  • Run

We take WER (Word Error Rate) as the metric. WER is computed as follows:

WER = Edit distance / Number of words

Total WER : 10731/23541=0.46

Check the results folder for details.