Next generation of word embeddings

Short talk on when to use word2vec, word rank, fast text. A small review of the theory of word2vec. Code in https://gist.github.com/tmylk/14f887f8585e9f89ab5896a10308447c

Transcript

1. Next generation of word embeddings Lev Konstantinovskiy Community Manager at Gensim @teagermylk http://rare-technologies.com/
2. Streaming Word2vec and Topic Modelling in Python
3. Gensim Open Source Package • Numerous Industry Adopters • 170 Code contributors, 4000 Github stars • 200 Messages per month on the mailing list • 150 People chatting on Gitter • 500 Academic citations
4. Gensim coding sprint Date: April Location: somewhere in BH, To Be Announced Interested? Contact me on pydatabh.slack.com Twitter @teagermylk lev@rare-technologies.com Topic: Learn machine learning by improving our tutorials.
5. Credits Parul Sethi Undergraduate student University of Delhi, India RaReTech Incubator program Added WordRank to Gensim http://rare-technologies.com/incubator/
7. Part 1. Different word embeddings Part 2. Theory of word2vec
8. Business Problems
9. Business Problems “What is Dona Flor like?” “List all female characters in “Dona Flor e seus dois maridos”?”
10. Two Different Business Problems 1) What words are in the topic of “Dona Flor”? 2) What are the Named Entities in the text?
11. DFDM is only 170k words so results are so-so
12. Teodoro
13. Closest word to “king”? Trained on Wikipedia 17m words Attribute Interchangeable Both
14. How to get the similarity you need My similar words must be Associated Interchangeable I want to describe 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
15. Part 2. Theory of Word2vec
16. Word2vec is big victory of unsupervised learning Google ran word2vec on 100billion of unlabelled words. Then shared their trained model. Thanks to Google for cutting our training time to zero!. :)
17. Word embeddings can be used for: - automated text tagging - recommendation engines - synonyms and search query expansion - machine translation - plain feature engineering
18. What is a word embedding? ‘Word embedding’ = ‘word vectors’ = ‘distributed representations’ It is a dense representation of words in a low-dimensional vector space. One-hot representation: king = [1 0 0 0.. 0 0 0 0 0] queen = [0 1 0 0 0 0 0 0 0] book = [0 0 1 0 0 0 0 0 0] king = [0.9457, 0.5774, 0.2224] Distributed representation:
19. Many other ways to get a vector for a word: - Factorise the co-occurence matrix (SVD/LSA) - GLoVe - EigenWords - WordRank - VarEmbed - FastText Disclaimer Word2vec is not the only word embedding in the world
21. Use the “Distributional hypothesis”: “You shall know a word by the company it keeps” -J. R. Firth 1957 Richard Socher’s NLP course http://cs224d.stanford.edu/lectures/CS224d-Lecture2.pdf How to come up with an embeddig?
22. Usual procedure 1.Initialise random vectors 2. Pick an objective function. 3. Do gradient descent.
23. For the theory, take Richard Sochers’s CS224D free online class Richard Socher’s NLP course http://cs224d.stanford.edu/lectures/CS224d-Lecture2.pdf
24. “The fox jumped over the lazy dog” Maximize the likelihood of seeing the context words given the word over. P(the|over) P(fox|over) P(jumped|over) P(the|over) P(lazy|over) P(dog|over) word2vec algorithm Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec
25. Probability should depend on the word vectors. Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec P(fox|over) P(v fox |v over )
26. A twist: two vectors for every word Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec Should depend on whether it’s the input or the output. P(v OUT |v IN ) “The fox jumped over the lazy dog” v IN
27. Twist: two vectors for every word Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec Should depend on whether it’s the input or the output. P(v OUT |v IN ) “The fox jumped over the lazy dog” v IN v OUT = P(v THE |v OVER )
28. Twist: two vectors for every word Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec Should depend on whether it’s the input or the output. P(v OUT |v IN ) “The fox jumped over the lazy dog” v IN v OUT
29. Twist: two vectors for every word Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec Should depend on whether it’s the input or the output. P(v OUT |v IN ) “The fox jumped over the lazy dog” v IN v OUT
30. Twist: two vectors for every word Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec Should depend on whether it’s the input or the output. P(v OUT |v IN ) “The fox jumped over the lazy dog” v IN v OUT
31. Twist: two vectors for every word Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec Should depend on whether it’s the input or the output. P(v OUT |v IN ) “The fox jumped over the lazy dog” v IN v OUT
32. Twist: two vectors for every word Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec Should depend on whether it’s the input or the output. P(v OUT |v IN ) “The fox jumped over the lazy dog” v IN v OUT
33. Twist: two vectors for every word Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec Should depend on whether it’s the input or the output. P(v OUT |v IN ) “The fox jumped over the lazy dog” v IN v OUT
34. Twist: two vectors for every word Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec Should depend on whether it’s the input or the output. P(v OUT |v IN ) “The fox jumped over the lazy dog” v IN v OUT
35. How to define P(v OUT |v IN )? First, define similarity. How similar are two vectors? Just dot product for unit length vectors v OUT * v IN Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec
36. Get a probability in [0,1] out of similarity in [-1, 1] Normalization term over all out words Used with permission from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec
37. Word2vec is great! Vector arithmetic Slide from @chrisemoody http://www.slideshare.net/ChristopherMoody3/word2vec-lda-and-introducing-a-new-hybrid-algorithm-lda2vec - -
38. @datamusing Sudeep Das http://www.slideshare.net/SparkSummit/using-data-science-to-transform-opentable-into-delgado-das More directions
39. Consistent directions Mikolov et al. Distributed Representations of Words and Phrases and their Compositionality 2013
40. Explore word2vec yourself http://rare-technologies.com/word2vec-tutorial/#app
41. Thanks! Lev Konstantinovskiy github.com/tmylk @teagermylk Contact me if interested Gensim sprint in BH (full day coding event)