Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization.
A Tensorflow implementation for "Interactive Attention Networks for Aspect-Level Sentiment Classification"
A Tensorflow Implementation of R-net: Machine reading comprehension with self matching networks
Extract MFCCs from videos and make bag-of-audio-words (BOAW) representations.
Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning; py3 version in py3 branch (it actually should be compatible to both py2 and py3)
