Merge pull request #11 from shreyasajal/master

Add files via upload

Summaries/GloVe Representation.md

@@ -0,0 +1,24 @@
+
+
+
+## **GloVe Representation Model**
+
+> **Quick Overview**
+     
+
+ 1.  A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods.
+ 2. The model efficiently leverages statistical information by training only on the nonzero elements in a word-word co-occurrence matrix, rather than on the entire sparse matrix or on individual context windows in a large corpus.
+
+
+>[ **Presentation made for the discussion**](https://docs.google.com/presentation/d/1UZZ35_wa9pQbZEIsC77SVpzC3XrrM5LACXiS0UOnOQg/edit?usp=sharing)
+
+
+>   [**Implementation through transfer learning**](https://colab.research.google.com/drive/1J75hTE5UFPKeO0GcV8os9YTILhptYDrY?usp=sharing)
+
+> **Resources**
+
+
+ 1. [Paper](https://www.aclweb.org/anthology/D14-1162/)
+ 2. [Video](https://www.youtube.com/watch?v=ASn7ExxLZws&t=3068s)
+ 3. [Pretrained word vectors](https://nlp.stanford.edu/projects/glove/)
+

Summaries/Word2Vec Representation.md

@@ -0,0 +1,25 @@
+
+
+
+## **Word2Vec Representation Model**
+
+> **Quick Overview**
+     
+
+ 1. The main goal of this paper is to introduce techniques that can be
+   used for learning high-quality word vectors from huge data sets with
+   billions of words, and with millions of words in the vocabulary.​
+
+ 2. It proposes two novel model architectures - CBOW and Skip-Gram ,   for computing continuous vector representations of words from very   large data sets.​
+
+
+
+> [**Presentation made for the discussion**](https://drive.google.com/file/d/1Hwi-Iy1tgr-N3zHoRFh0pLE5PN6cuk3s/view?usp=sharing)
+
+
+> **Resources**
+> 
+
+ 1. [Paper](https://arxiv.org/abs/1301.3781)
+ 2. [Video](https://www.youtube.com/watch?v=ERibwqs9p38)
+