# CS224n-2019-solutions

**Repository Path**: thb1314/CS224n-2019-solutions

## Basic Information

- **Project Name**: CS224n-2019-solutions
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2020-04-18
- **Last Updated**: 2021-06-20

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

<a href="https://996.icu"><img src="https://img.shields.io/badge/link-996.icu-red.svg" alt="996.icu"></a>

# CS224n-winter19

Solutions for **CS224n, winter, 2019.**    
Welcome to discuss problems appearing in assigments, **please** submit to issue.    
Also take notes for the key point in lectures.
The solutions for assignment is written by **Markdown** in [Assignments/written part](https://github.com/ZacBi/CS224n-2019-solutions/tree/master/Assignments/written%20part).
&nbsp;
- Course page: https://web.stanford.edu/class/cs224n
- Video page: https://www.youtube.com/watch?v=8rXD5-xhemo&list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z


<!-- CS224n-win-2019练习答案。    
问题请提交至issue，欢迎各位一起讨论。    
需要书写的答案都是用**Markdown**写的，内容为全英文。    
水平有限，望各位不吝指教。    
部分答案有缺失，紧急补课中···     -->
***

## Update

## update 2019/12/03

&emsp;&emsp;After CS224n I realize that more systematical training is needed. So I start a new repo [learn_NLP_again](https://github.com/ZacBi/learn_NLP_again), here is the description(algorithms and solutions is available for chapter 1 until now):

> &emsp;&emsp;Here is why I started this project: **learn NLP from scratch again**. I choose [Speech and language process](https://web.stanford.edu/~jurafsky/slp3/) as my entry point, and try to write solutions and implement some algorithms/models of this book. I hope I can stick to this project and update frequently.

&emsp;&emsp;After one year's training in corporation and lab, I find many faults or incorrect habbits in past parctice, (btw, there is too many commits in this repo). I'll review the code in this repo and solve issues gradually.(:smile:, hopefully)

**Welcome communications in new repo!**


## w1

### reading

- [x] note:&ensp;Word Vectors I: Introduction, SVD and Word2Ve
- [x] Word2Vec Tutorial - The Skip-Gram Model
&nbsp;

### practice

- [x] coding: Assignment1
- [x] Gensim

## w2

### reading

- [x] note:&ensp;Word Vectors II: GloVe, Evaluation and Trainin
- [x] gradient-notes
- [x] CS231n notes on backprop
- [x] review-differential-calculus
- [x] backprop_old
- [x] CS231n notes on network architectures

### practice

- [x] coding: Assignment2
- [x] writing: Assignment2

## **w3**

### reading

- [x] note:&ensp;Dependency Parsing 
- [x] note:&ensp;Language Models and Recurrent Neural Network
- [x] a3

### practice

- [x] coding: Assignment3
- [x] writing: Assignment3

## **w4**

### reading

- [x] note:&emsp;Machine Translation, Sequence-to-sequence and Attention
- [x] a4
- [x] read:&emsp;Attention and Augmented Recurrent Neural Networks
- [x] read:&emsp;Massive Exploration of Neural Machine Translation Architectures (practical advice for hyperparameter choices)

### practice

- [x] coding: Assignment4
- [x] writing: Assignment4


### key point for a4

How to understand pack_padded_sequence and pad_packed_sequence?    
[(Chinese ed)](https://blog.csdn.net/lssc4205/article/details/79474735)    
[(English ed)](https://gist.github.com/HarshTrivedi/f4e7293e941b17d19058f6fb90ab0fec)

## **w5**

It has been long time for no updating...

### reading

- [x] note:&emsp;Machine Translation, Sequence-to-sequence and Attention
- [x] a4
- [x] read:&emsp;Attention and Augmented Recurrent Neural Networks

### practice

- [x] coding: Assignment5
- [x] writing: Assignment5

## Final project

**reading**:

- [x] final-project-practical-tips
- [x] default-final-project-handout
- [x] project-proposal-instructions
- [x] Practical Methodology_Deep Learning book chapter
- [x] Highway Networks
- [x] Bidirectional Attention Flow for Machine Comprehension

**practice**:

- [x] anotate codes
- [x] train baseline