NLP_Training

NLP examples

Check the How to run the code.txt file on how to use these notebooks.

We have downloaded the word embeddings and datasets from these links:

Word Embeddings:
Glove: https://github.com/stanfordnlp/GloVe/blob/master/README.md
Fast Text: https://fasttext.cc/docs/en/english-vectors.html
LexVec: https://github.com/alexandres/lexvec
ConceptNet NumberBatch: https://github.com/commonsense/conceptnet-numberbatch
Google News: https://code.google.com/archive/p/word2vec/
PDC: http://ofey.me/projects/wordrep/
HDC: http://ofey.me/projects/wordrep/

Similarity datasets:

MTurk : Available on this repo
MEN : Available on this repo
WS353 : http://www.cs.technion.ac.il/~gabr/resources/data/wordsim353/ also available on this repo
RG65 : Available on this repo
RW : https://nlp.stanford.edu/~lmthang/morphoNLM/ also available on this Available on this repo
SimLex999 :https://fh295.github.io/simlex.html
TR9856 : Available on this repo

Analogy datasets MSR WordRep : Available on this repo
Google Analogy : Available on this repo
MSR : Available on this repo
SEMEVAL 2012 Task 2 : Available on this repo

Important references for Text classification with PyTorch https://www.analyticsvidhya.com/blog/2020/01/first-text-classification-in-pytorch/

https://github.com/pchampio/sentence-entailment

Description of Experiments file:

Model Description LSTIM(Bidirectional, Number of Layers, Num of Hidden Nodes, Dropout rate)