Frameworks for deep learning with dynamic graphs construction

Two frameworks PyTorch and DyNet are released recently. They both feature dynamic graph construction, which is more flexible than current frameworks like Tensorflow and Theano, with other features of their own. (though Tensorflow has some functions for dynamic NN architecture construction)

DyNet: https://arxiv.org/abs/1701.03980

PyTorch: http://pytorch.org/


Update on Feb 16:

Tensorflow accounced a new feature called Tensorflow Fold, which supports dynamic computation graphs. More importantly, different from the above two, it also supports dynamic batching, which makes it more powerful. I would expect other frameworks like MXNet/Pytorch/others will support the function as well very soon.

Details here:

 

More to be continued on these topics soon.

 

Review of Neural Machine Translation

This is a post that reviews the recent advancements of machine translation, especially neural machine translation (NMT). 

Prerequisites: this post assumes some prior knowledge about machine learning, artificial neural networks, CNN, RNN (LSTM, GRU) encoder-decoder architecture, seq-to-seq models, etc. Continue reading

Word Embedding/Word Vector/Word Representation in NLP

This is a post that summarizes the fundamental approaches to representing a word in NLP.  I found that it’ll make me better understand a concept if I write it down and make some reviewing on it.

Basically, this post tries to answer the question: how to represent a word in a sentence for various applications of NLP?

Continue reading

Literature Review on Rare Word Issue in Neural Machine Translation

Here is a link to a literature review I made on the topic of rare word issue and its approaches in neural machine translation. It briefly introduces neural machine translation, and then focuses on the specific present solutions to rare word issue in NMT. Feel free to make comments on it.

https://drive.google.com/open?id=0Bxp-YYmYjAazYVB1ZEFsYkhHdXc