hankcs / Cs224n
Licence: gpl-3.0
CS224n: Natural Language Processing with Deep Learning Assignments Winter, 2017
Stars: ✭ 656
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Cs224n
Gensim
Topic Modelling for Humans
Stars: ✭ 12,763 (+1845.58%)
Mutual labels: natural-language-processing, word2vec
Deepnlp Models Pytorch
Pytorch implementations of various Deep NLP models in cs-224n(Stanford Univ)
Stars: ✭ 2,760 (+320.73%)
Mutual labels: natural-language-processing, rnn
Deep Math Machine Learning.ai
A blog which talks about machine learning, deep learning algorithms and the Math. and Machine learning algorithms written from scratch.
Stars: ✭ 173 (-73.63%)
Mutual labels: natural-language-processing, word2vec
Awesome Embedding Models
A curated list of awesome embedding models tutorials, projects and communities.
Stars: ✭ 1,486 (+126.52%)
Mutual labels: natural-language-processing, word2vec
altair
Assessing Source Code Semantic Similarity with Unsupervised Learning
Stars: ✭ 42 (-93.6%)
Mutual labels: word2vec, rnn
Scattertext
Beautiful visualizations of how language differs among document types.
Stars: ✭ 1,722 (+162.5%)
Mutual labels: natural-language-processing, word2vec
Practical 1
Oxford Deep NLP 2017 course - Practical 1: word2vec
Stars: ✭ 220 (-66.46%)
Mutual labels: natural-language-processing, word2vec
Pytorch Pos Tagging
A tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.
Stars: ✭ 96 (-85.37%)
Mutual labels: natural-language-processing, rnn
DeepLearning-Lab
Code lab for deep learning. Including rnn,seq2seq,word2vec,cross entropy,bidirectional rnn,convolution operation,pooling operation,InceptionV3,transfer learning.
Stars: ✭ 83 (-87.35%)
Mutual labels: word2vec, rnn
chainer-notebooks
Jupyter notebooks for Chainer hands-on
Stars: ✭ 23 (-96.49%)
Mutual labels: word2vec, rnn
Magnitude
A fast, efficient universal vector embedding utility package.
Stars: ✭ 1,394 (+112.5%)
Mutual labels: natural-language-processing, word2vec
Text summurization abstractive methods
Multiple implementations for abstractive text summurization , using google colab
Stars: ✭ 359 (-45.27%)
Mutual labels: rnn, word2vec
Repo 2016
R, Python and Mathematica Codes in Machine Learning, Deep Learning, Artificial Intelligence, NLP and Geolocation
Stars: ✭ 103 (-84.3%)
Mutual labels: natural-language-processing, word2vec
Scattertext Pydata
Notebooks for the Seattle PyData 2017 talk on Scattertext
Stars: ✭ 132 (-79.88%)
Mutual labels: natural-language-processing, word2vec
Codesearchnet
Datasets, tools, and benchmarks for representation learning of code.
Stars: ✭ 1,378 (+110.06%)
Mutual labels: natural-language-processing, rnn
Germanwordembeddings
Toolkit to obtain and preprocess german corpora, train models using word2vec (gensim) and evaluate them with generated testsets
Stars: ✭ 189 (-71.19%)
Mutual labels: natural-language-processing, word2vec
Sense2vec
🦆 Contextually-keyed word vectors
Stars: ✭ 1,184 (+80.49%)
Mutual labels: natural-language-processing, word2vec
Ja.text8
Japanese text8 corpus for word embedding.
Stars: ✭ 79 (-87.96%)
Mutual labels: natural-language-processing, word2vec
Pytorch Sentiment Analysis
Tutorials on getting started with PyTorch and TorchText for sentiment analysis.
Stars: ✭ 3,209 (+389.18%)
Mutual labels: natural-language-processing, rnn
Languagecrunch
LanguageCrunch NLP server docker image
Stars: ✭ 281 (-57.16%)
Mutual labels: natural-language-processing, word2vec
CS224n
CS224n: Natural Language Processing with Deep Learning Assignments Winter, 2017
Requirements
- Python 2.7
- TensorFlow r1.2
Assignment #1
- Softmax
- Neural Network Basics
- word2vec
- Sentiment Analysis
Assignment #2
- Tensorflow Softmax
- Neural Transition-Based Dependency Parsing
924/924 [==============================] - 49s - train loss: 0.0631
Evaluating on dev set - dev UAS: 88.54
New best dev UAS! Saving model in ./data/weights/parser.weights
================================================================================
TESTING
================================================================================
Restoring the best model weights found on the dev set
Final evaluation on test set - test UAS: 88.92
Writing predictions
Done!
- Recurrent Neural Networks: Language Modeling
Assignment #3
- A window into NER
DEBUG:Token-level confusion matrix:
go\gu PER ORG LOC MISC O
PER 2968 26 84 16 55
ORG 147 1621 131 65 128
LOC 48 88 1896 26 36
MISC 37 40 54 1030 107
O 42 46 18 39 42614
DEBUG:Token-level scores:
label acc prec rec f1
PER 0.99 0.92 0.94 0.93
ORG 0.99 0.89 0.77 0.83
LOC 0.99 0.87 0.91 0.89
MISC 0.99 0.88 0.81 0.84
O 0.99 0.99 1.00 0.99
micro 0.99 0.98 0.98 0.98
macro 0.99 0.91 0.89 0.90
not-O 0.99 0.89 0.87 0.88
INFO:Entity level P/R/F1: 0.82/0.85/0.84
- Recurrent neural nets for NER
DEBUG:Token-level confusion matrix:
go\gu PER ORG LOC MISC O
PER 2987 32 47 12 71
ORG 136 1684 90 70 112
LOC 39 83 1907 21 44
MISC 43 45 47 1031 102
O 36 56 15 34 42618
DEBUG:Token-level scores:
label acc prec rec f1
PER 0.99 0.92 0.95 0.93
ORG 0.99 0.89 0.80 0.84
LOC 0.99 0.91 0.91 0.91
MISC 0.99 0.88 0.81 0.85
O 0.99 0.99 1.00 0.99
micro 0.99 0.98 0.98 0.98
macro 0.99 0.92 0.89 0.91
not-O 0.99 0.90 0.88 0.89
INFO:Entity level P/R/F1: 0.85/0.86/0.85
- Grooving with GRUs
DEBUG:Token-level confusion matrix:
go\gu PER ORG LOC MISC O
PER 2920 41 57 12 119
ORG 101 1716 73 64 138
LOC 22 95 1908 16 53
MISC 37 45 53 1017 116
O 21 67 14 39 42618
DEBUG:Token-level scores:
label acc prec rec f1
PER 0.99 0.94 0.93 0.93
ORG 0.99 0.87 0.82 0.85
LOC 0.99 0.91 0.91 0.91
MISC 0.99 0.89 0.80 0.84
O 0.99 0.99 1.00 0.99
micro 0.99 0.98 0.98 0.98
macro 0.99 0.92 0.89 0.90
not-O 0.99 0.91 0.88 0.89
INFO:Entity level P/R/F1: 0.86/0.85/0.85
- Easter Egg Hunt!
- Run
python q3_gru.py dynamicsto unfold your candy eggs
- Run
References
CS224n official website
Many code snippets come from
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].