Lecture 1: Introduction Kai-Wei Chang CS @ UCLA kw@kwchang.net - - PowerPoint PPT Presentation
Lecture 1: Introduction Kai-Wei Chang CS @ UCLA kw@kwchang.net Couse webpage: https://uclanlp.github.io/CS269-17/ ML in NLP 1 Announcements v Waiting list: Start attending the first few lectures as if you are registered. Given that some
Kai-Wei Chang CS @ UCLA kw@kwchang.net Couse webpage: https://uclanlp.github.io/CS269-17/
1 ML in NLP
ML in NLP 2
3 ML in NLP
ML in NLP 4
ML in NLP 5
ML in NLP 6
ML in NLP 7
Facebook translation, image credit: Meedan.org
ML in NLP 8
Image credit: Julia Hockenmaier, Intro to NLP
ML in NLP 9
ML in NLP 10
ML in NLP 11
www.wired.com
ML in NLP 12
credit: ifunny.com
'Watson' computer wins at 'Jeopardy'
ML in NLP 13
ML in NLP 14
https://youtu.be/KkOCeAtKHIc?t=1m28s
ML in NLP 15
credit: techspot.com
ML in NLP 16
Yoav Artzi: Natural language processing
ML in NLP 17
ML in NLP 18
ML in NLP 19
ML in NLP 20
ML in NLP 21
ML in NLP 22
ML in NLP 23
ML in NLP 24
ML in NLP 25
ML in NLP 26
ML in NLP 27
ML in NLP 28
ML in NLP 29
ML in NLP 30
ML in NLP 31
ML in NLP 32
ML in NLP 33
ML in NLP 34
ML in NLP 35
ML in NLP 36
Credit: http://stuffsirisaid.com
ML in NLP 37
Credit: Mark Liberman, http://languagelog.ldc.upenn.edu/nll/?p=17711
ML in NLP 38
ML in NLP 39
Credit: http://www.printwand.com/blog/8-catastrophic-examples-of-word-choice-mistakes
ML in NLP 40
ML in NLP 41
ML in NLP 42
ML in NLP 43
ML in NLP 44
ML in NLP 45
ML in NLP 46
ML in NLP 47
Image credit: Julia Hockenmaier, Intro to NLP
ML in NLP 48
ML in NLP 49
Credit: Ivan Titov
50
Slide modified from Dan Roth ML in NLP
51
ML in NLP
ML in NLP 52
CS6501- Advanced Machine Learning 53
CS6501- Advanced Machine Learning 54
CS6501- Advanced Machine Learning 55
CS6501- Advanced Machine Learning 56
CS6501- Advanced Machine Learning 57
58
Bill Clinton, recently elected as the President of the USA, has been invited by the Russian President], [Vladimir Putin, to visit Russia. President Clinton said that he looks forward to strengthening ties between USA and Russia
Algorithm 2 is shown to perform better Berg-Kirkpatrick, ACL
converge faster -- anyway, the E- step changes the auxiliary function by changing the expected counts, so there's no point in finding a local maximum
function in each iteration a local-optimality guarantee. Consequently, LOLS can improve upon the reference policy, unlike previous
develop structured contextual bandits, a partial information structured prediction setting with many potential applications. Can learning to search work even when the reference is poor? We provide a new learning to search algorithm, LOLS, which does well relative to the reference policy, but additionally guarantees low regret compared to deviations from the learned policy. Methods for learning to search for structured prediction typically imitate a reference policy, with existing theoretical guarantees demonstrating low regret compared to that reference. This is unsatisfactory in many applications where the reference policy is suboptimal and the goal
Robin is alive and well. He is the same person that you read about in the book, Winnie the Pooh. As a boy, Chris lived in a pretty home called Cotchfield Farm. When Chris was three years old, his father wrote a poem about
magazine for others to read. Mr. Robin then wrote a book Robin is alive and well. He is the same person that you read about in the book, Winnie the Pooh. As a boy, Chris lived in a pretty home called Cotchfield
his father wrote a poem about him. The poem was printed in a magazine for
book
CS6501- Advanced Machine Learning 59
Robin is alive and well. He is the same person that you read about in the book, Winnie the Pooh. As a boy, Chris lived in a pretty home called Cotchfield
his father wrote a poem about him. The poem was printed in a magazine for
book
CS6501- Advanced Machine Learning 60
CS6501- Advanced Machine Learning 61
CS6501- Advanced Machine Learning 62
CS6501- Advanced Machine Learning 63
CS6501- Advanced Machine Learning 64
CS6501- Advanced Machine Learning 65 Example from Vivek Srikumar
v Assign tag (V., N., A., …) to each word in the sentence
v Cannot have verb followed by a verb
CS6501- Advanced Machine Learning 66
v have multiple interdependent output variables
CS6501- Advanced Machine Learning 67
68
I can can a can Pro Md Vb Dt Nn Pro Md Nn Dt Vb Pro Md Nn Dt Md Pro Md Md Dt Nn Pro Md Md Dt Vb
Kai-Wei Chang (University of Virginia)
69
I can can a can Pro Md Vb Dt Nn Pro Md Nn Dt Vb Pro Md Nn Dt Md Pro Md Md Dt Nn Pro Md Md Dt Vb
Kai-Wei Chang (University of Virginia)
CS6501- Advanced Machine Learning 70
Pronoun Verb Noun And Noun
Root They operate ships and banks .
CS6501- Advanced Machine Learning 71
CS6501- Advanced Machine Learning 72
Robin is alive and well. He is the same person that you read about in the book, Winnie the Pooh. As a boy, Chris lived in a pretty home called Cotchfield
wrote a poem about him. The poem was printed in a magazine for others to read. Mr. Robin then wrote a book
CS6501- Advanced Machine Learning 73
When Chris was three years old, his father wrote a poem about him. Christopher Robin is alive and well. He is the same person that you read about in the book, Winnie the Pooh. As a boy, Chris lived in a pretty home called Cotchfield Farm.
CS6501- Advanced Machine Learning 74
Robin is alive and well. He is the same person that you read about in the book, Winnie the Pooh. As a boy, Chris lived in a pretty home called Cotchfield Farm. When Chris was three years old, his father wrote a poem about him. The poem was printed in a magazine for others to read. Mr. Robin then wrote a book
v # English words: 171K (Oxford) v # Bigram: 171𝐿 H~3×10<=, # trigram?
CS6501- Advanced Machine Learning 75
CS6501- Advanced Machine Learning 76
CS6501- Advanced Machine Learning 77
CS6501- Advanced Machine Learning 78