NATURAL LANGUAGE PROCESSING

1
CHAPTER 13

• NATURAL LANGUAGE PROCESSING

2
Machine Translation
3
Information Extraction
4
Question Answering
5
Some Early NLP History
6
Why is Language Hard?

• Ambiguity
• ? Eye Drops Off Shelf
• ? Miners Refuse to Work After Death
• ? Killer Sentenced to Die for Second Time in 1
• Years
• ? Iraqi Head Seeks Arms
• ? Ban on Nude Dancing on Governors Desk
• ? Juvenile Court to Try Shooting Defendant
• ? Stolen Painting Found by Tree
• ? Local HS Dropouts Cut in Half
• ? Hospitals Are Sued by 7 Foot Doctors

7
Models of Language
8
Language Modeling
9
Unigram Models
10
Bigram Models
11
Human Processing
12
Why is Language Hard?
13
Parsing as Search Top-Down
14
Corpus-Based Methods
15
Semantic Interpretation

• On to meaning!
• ? A very basic approach to computational
  semantics
• ? Truth-theoretic notion of semantics (Tarskian)
• ? Assign a meaning to each word
• ? Word meanings combine according to the parse
• structure
• ? People can and do spend entire courses on this
  
• topic
• ? Well spend under an hour!
• Whats NLP and whats general AI?
• ? Designing meaning representations?
• ? Computing those representations?
• ? Reasoning with them?

16
Problem Ambiguities

• Headlines
• ? Iraqi Head Seeks Arms
• ? Ban on Nude Dancing on Governors Desk
• ? Juvenile Court to Try Shooting Defendant
• ? Teacher Strikes Idle Kids
• ? Stolen Painting Found by Tree
• ? Kids Make Nutritious Snacks
• ? Local HS Dropouts Cut in Half
• ? Hospitals Are Sued by 7 Foot Doctors
• Why are these funny?

17
Machine Translation
18
Just a Code?

• Also knowing nothing official about, but having
  guessed and
• inferred considerable about, the powerful new
  mechanized
• methods in cryptographymethods which I believe
  succeed
• even when one does not know what language has
  been
• codedone naturally wonders if the problem of
  translation
• could conceivably be treated as a problem in
  cryptography.
• When I look at an article in Russian, I say
  This is really
• written in English, but it has been coded in
  some strange
• symbols. I will now proceed to decode.
• Warren Weaver (195518, quoting a letter he wrote
  in 1947)

19
Levels of Transfer
20
Memory Theory
21
Time Theory
22
Problem Scale
23
Problem Sparsity