Init README.md

Author: glitch401

README.md

@@ -1,2 +1,20 @@
-# LanguageTechnologyPytorch
-Implementation of various Natural Language Processing using PyTorch
+
+# Natural Language Processing using PyTorch
+Hype around Deep Learning is centered mostly around Computer Vision, so are gateways to understanding most of the popular frameworks. With the recent advances around Language Technology/ Computational Linguistics or Natural Language Processing as popularly known, getting proper resources to engulf and fully understand the machinations behind it is arduous for starters.
+
+Hence this project is inspired by specialization course of [Natural Language Processing](https://www.coursera.org/specializations/natural-language-processing) by [deeplearning.ai](https://www.deeplearning.ai/) offered through [Coursera](https://www.coursera.org) instructed by [Younes Bensouda Mourri](https://www.coursera.org/instructor/ymourri), [Łukasz Kaiser](https://www.coursera.org/instructor/lukaszkaiser), et.al.
+
+`PyTorch` has been chosen due to its popularity in academia.
+
+## NLP Tasks:
+| Module | Content | Status |
+|--|--|--|
+| 2 | Neural network with GLoVe `word embeddings` to perform `sentiment analysis` of Tweets |  <ul><li> [ ] </li></ul>  |
+| 2 | `Crosslingual Multi-Aspect` sentiment analysis using `sentence embeddings` |  <ul><li> [ ] </li></ul>  |
+| 2 | `Generate` synthetic Shakespeare `text` using a Gated Recurrent Unit (`GRU`) language model |  <ul><li> [ ] </li></ul>  |
+| 2 | Named Entity Recognition (`NER`) using `LSTM`s |  <ul><li> [ ] </li></ul>  |
+| 2 | `Siamese` LSTM to analyse `similar` questions |  <ul><li> [ ] </li></ul>  |
+| 2 | `Machine Translation` using `Attention` |  <ul><li> [ ] </li></ul>  |
+<!---| 1 | `Basics`: <ul><li> Sentiment analysis of tweets using `logistic regression` and `naïve Bayes` </li><li>  `PCA` for dimension reduction of vector space</li><li>Translation using pre-trained embeddings with `locality sensitive hashing` and approximation with `k-nearest neighbor` search</li></ul> |  <ul><li> [ ] </li><li> [ ] </li><li> [ ] </li></ul>  |
+| 1 | `Probabilistic Models`: <ul><li> Auto-correct algorithm using `Levenshtein`/`minimum edit distance` and n-gram language model </li><li>  `Viterbi` Algorithm for part-of-speech (`POS`) tagging</li><li>`Word2Vec` model that using continuous bag-of-words(`CBOW`)</li></ul> |  <ul><li> [ ] </li><li> [ ] </li><li> [ ] </li></ul>  |-->
+