Keep Current :: NLP Seminar #1 - Dimension Reduction


Details
Machine Learning Seminar #1 - Dimension Reduction in Natural Language Processing
Level: Advanced
This is the first event in a series of seminars for approaching, understanding and working with Machine learning from different perspectives. These events are not a lectures, but rather discussions, with the aim of learning from each other perspective.
This event will focus on dimension reduction aspects in the field of Natural Language Processing.
We will discuss and explore similarities and differences across varying methodologies - from PCA and LDA to GloVe and FastText - in an attempt to understand better the best uses and limitations of these tools.
The seminar format works best if you come prepared. Please check the reading list below and bring your own insights, questions, and perplexities to the table!
This is our recommended reading list:
LDA
http://www.jmlr.org/papers/volume3/blei03a/blei03a.pdf
T-SNE
https://www.youtube.com/watch?v=RJVL80Gg3lA
PCA
https://medium.com/@aptrishu/understanding-principle-component-analysis-e32be0253ef0
http://setosa.io/ev/principal-component-analysis/
Word2vec
-
https://www.tensorflow.org/tutorials/representation/word2vec
-
https://towardsdatascience.com/word-embedding-with-word2vec-and-fasttext-a209c1d3e12c
GloVe
https://nlp.stanford.edu/pubs/glove.pdf
TECHNIQUES COMPARISSON
https://www.analyticsvidhya.com/blog/2018/08/dimensionality-reduction-techniques-python/
https://arxiv.org/ftp/arxiv/papers/1403/1403.2877.pdf
Please feel free to add more sources in the comments.
We look forward to seeing you!

Keep Current :: NLP Seminar #1 - Dimension Reduction