Implementation of research papers on Deep Learning+ NLP+ CV in Python using Keras, Tensorflow and Scikit Learn.
Clone or download
Latest commit a69ba66 Apr 16, 2018

README.md

DeepLearn

Welcome to DeepLearn. This repository contains implementation of following research papers on NLP, CV, ML, and deep learning. Visit my blog for more details - Deeplearn

- Latest Update : Added _deeplearn_utils modules. Check the releases for description of new features.

[1] Correlation Neural Networks. CV, transfer learning, representation learning. blog-post || code

[2] Reasoning With Neural Tensor Networks for Knowledge Base Completion. NLP, ML. blog-post || code

[3] Common Representation Learning Using Step-based Correlation Multi-Modal CNN. CV, transfer learning, representation learning. code

[4] ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs. NLP, deep learning, sentence matching. code

[5] Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks. NLP, deep learning, CQA. code

[6] Combining Neural, Statistical and External Features for Fake News Stance Identification. NLP, IR, deep learning. code

[7] WIKIQA: A Challenge Dataset for Open-Domain Question Answering. NLP, deep learning, CQA. code

[8] Siamese Recurrent Architectures for Learning Sentence Similarity. NLP, sentence similarity, deep learning. code

[9] Convolutional Neural Tensor Network Architecture for Community Question Answering. NLP, deep learning, CQA. code

[10] Map-Reduce for Machine Learning on Multicore. map-reduce, hadoop, ML. code

[11] Teaching Machines to Read and Comprehend. NLP, deep learning. code

[12] Improved Representation Learning for Question Answer Matching. NLP, deep learning, CQA. code

[13] External features for community question answering. NLP, deep learning, CQA. code

[14] Language Identification and Disambiguation in Indian Mixed-Script. NLP, IR, ML. blog-post || code

[15] Construction of a Semi-Automated model for FAQ Retrieval via Short Message Service. NLP, IR, ML. code

Dependencies:

The required dependencies are mentioned in requirement.txt. I will also use dl-text modules for preparing the datasets. If you haven't use it, please do have a quick look at it.

$ pip install -r requirements.txt