1. From Language to Information
[These slides were originally created by Dan Jurafsky from Stanford]

2. From language to information
For humans, going from the largely unstructured languages of the web to information is effortlessly easy
But it’s hard for computers!
Build the next generation of intelligent agents to make decisions on your behalf
Answering your routine
Booking your next trip to Fiji
they need to be able to go from languages to information

3. What this course is about
Automatically extracting meaning and structure from:
Human language text
Speech
Web pages
Social networks (and other networks)
Interacting with humans on-line via language
Question Answering
Personal Assistants
Chatbots

4. Question Answering: IBM’s Watson
Won Jeopardy on February 16, 2011!
WILLIAM WILKINSON’S
“AN ACCOUNT OF THE PRINCIPALITIES OF WALLACHIA AND MOLDOVIA”
INSPIRED THIS AUTHOR’S
MOST FAMOUS NOVEL
Bram Stoker
Stoker was an Irish author, best known today for his 1897 Gothic novel Dracula.

5. Information Extraction
Event: Curriculum mtg
Date: Jan
Start: 10:00am
End: 11:30am
Where: Gates 159
Subject: curriculum meeting Date: January 15, 2012 To: Dan Jurafsky Hi Dan, we’ve now scheduled the curriculum meeting. It will be in Gates 159 tomorrow from 10:00-11:30. -Chris
Create new Calendar entry

6. Information Extraction & Sentiment Analysis
Attributes:
zoom
affordability
size and weight
flash
ease of use
Size and weight ✓
nice and compact to carry!
since the camera is small and light, I won't need to carry around those heavy, bulky professional cameras either!
the camera feels flimsy, is plastic and very light in weight you have to be very delicate in the handling of this camera ✓ ✗

7. Language Technology making good progress still really hard
Sentiment analysis
still really hard
mostly solved
Best roast chicken in San Francisco!
Question answering (QA)
The waiter ignored us for 20 minutes.
Q. How effective is ibuprofen in reducing fever in patients with acute febrile illness?
Spam detection
Coreference resolution ✓
Let’s go to Agra! ✗
Paraphrase
Carter told Mubarak he shouldn’t run again.
Buy V1AGRA …
Word sense disambiguation (WSD)
XYZ acquired ABC yesterday
Part-of-speech (POS) tagging
I need new batteries for my mouse.
ABC has been taken over by XYZ
ADJ ADJ NOUN VERB ADV
Summarization
Parsing
Colorless green ideas sleep furiously.
The Dow Jones is up
Economy is good
I can see Alcatraz from the window!
The S&P500 jumped
Named entity recognition (NER)
Housing prices rose
Machine translation (MT)
PERSON ORG LOC
Dialog
第13届上海国际电影节开幕…
Where is Citizen Kane playing in SF?
Einstein met with UN officials in Princeton
The 13th Shanghai International Film Festival…
Castro Theatre at 7:30. Do you want a ticket?
Information extraction (IE)
Party May 27 add
You’re invited to our dinner party, Friday May 27 at 8:30

8. Ambiguity makes NLP hard
Teacher strikes idle kids. Red tape holds up new bridges. Hospitals are sued by 7 foot doctors. Local high school dropouts cut in half. Police police police.
Police must often police other police. QC

9. Greek grammar is exacting.
It is highly inflected to avoid vagueness.
Subject-verb connection is easily identifiable in even the most complex sentences.
Antecedents are less difficult to trace.
Modifiers will agree with the words they modify.
Huge vocabulary is helpful for expressing thoughts clearly without confusion.
A highly defined verb system concerning time and aspect.

10. Why else is natural language understanding difficult?
non-standard English
segmentation issues
idioms
Great Were SOO PROUD of what youve accomplished! U taught us 2 #neversaynever & you yourself should never give up either♥
dark horse
get cold feet
lose face
throw in the towel
the New York-New Haven Railroad
neologisms
world knowledge
tricky entity names
unfriend
Retweet
bromance
Mary and Sue are sisters.
Mary and Sue are mothers.
Where is A Bug’s Life playing …
Let It Be was recorded …
… a mutation on the for gene …
But that’s what makes it fun!

11. Making progress on this problem…
The task is difficult! What tools do we need?
Knowledge about language
Knowledge about the world
A way to combine knowledge sources
How we generally do this:
probabilistic models built from language data

12. Blog Analytics
Data-mining of blogs, discussion forums, message boards, user groups, and other forms of user generated media
Product marketing information
Political opinion tracking
Social network analysis
Buzz analysis (what’s hot, what topics are people talking about right now).

13. Extracting social meaning from Speech
Annoyance
Deception
Emotion
Intoxication
Flirtation, Romantic interest

14. Analyzing Restaurant Reviews
Yelp reviews online
A very bad (one-star) review:
The bartender... absolutely horrible... we waited 10 min before we even got her attention... and then we had to wait 45 - FORTY FIVE! - minutes for our entrees… stalk the waitress to get the cheque… she didn't make eye contact or even break her stride to wait for a response …

15. People who write after tragedies
Past tense: distancing from events
Use of “we”: seeking solace in community

16. Recommendation Engines

17. Ambiguity I made her duck. I cooked waterfowl for her benefit (to eat)
I cooked waterfowl belonging to her
I created the (plaster?) waterfowl she owns
I caused her to quickly lower her head or body
I waved my magic wand and turned her into undifferentiated waterfowl

18. I made her duck. I caused her to quickly lower her head or body
Part of speech: “duck” can be a Noun or Verb
I cooked waterfowl belonging to her.
Part of speech:
“her” is possive pronoun (“of her”)
“her” is dative pronoun (“for her”)
I made the (plaster) duck statue she owns
Word Meaning : “make” can mean “create” or “cook”

19. Lexical analysis Syntax analysis Semantic analysis Pragmatic analysis
Four Phases of NLP
Lexical analysis
Syntax analysis
Semantic analysis
Pragmatic analysis