Get the text similarity you need with word embeddings

Transcript

1. Get the word similarity you need Lev Konstantinovskiy Community Manager

   at Gensim @teagermylk http://rare-technologies.com/

2. Streaming We turn NLP papers into industrial Python code.

3. Credits Parul Sethi Undergraduate student University of Delhi, India RaReTech

   Incubator program Added WordRank to Gensim http://rare-technologies.com/incubator/

4. Business Problems

5. Business Problems “What does Elizabeth think about Mr Darcy?” “Male

   characters in Pride and Prejudice?”

6. Two Different Business Problems 1) What words are in the

   topic of “Darcy”? 2) What are the Named Entities in the text?

7. P&P is only 120k words

8. Closest word to “king”? Trained on Wikipedia 17m words Attribute

   Interchangeable Both

9. Tensorflow has awesome viz!

10. How to get the similarity you need My similar words

    must be Associated Interchangeable I want to describes the word’s Topic Function I want to Know what doc is about Recognize names Then I should run Wordrank (even on small corpus, 1m words) or Word2vec skipgram big window needs large corpus >5m words Word2vec skipgram small window or FastText or VarEmbed

11. Rare and Frequent words are incomprehensible

12. Thanks! Lev Konstantinovskiy github.com/tmylk @teagermylk Gensim T-shirt question: How many

    words are in Pride and Prejudice?