Understanding Natural Language

1
Understanding Natural Language
13
13.0 Role of Knowledge in Language Understanding
13.1 Deconstructing Language A
Symbolic Analysis 13.2 Syntax 13.3 Syntax and
Knowledge with ATN parsers
13.4 Stochastic Tools for Language
Analysis 13.5 Natural Language Applications 13.6
Epilogue and References 13.7 Exercises
Additional sources used in preparing the
slides Patrick H. Winstons AI textbook, Addison
Wesley, 1993.
2
Chapter Objective

• Give a brief introduction to the techniques used
  in understanding natural language

3
An early natural language understanding system
SHRDLU (Winograd, 1972)
4
It could converse about a blocks world

• What is sitting on the red block?
• What shape is the blue block on the table?
• Place the green cylinder on the red brick.
• What color is the block on the red block? Shape?

5
Stages of language analysis

• 1. Parsing analyze the syntactic structure of a
  sentence
• 2. Semantic interpretation analyze the meaning
  of a sentence
• 3. Contextual/world knowledge representation
  Analyze the expanded meaning of a sentence
• For instance, consider the sentence
• Tarzan kissed Jane.

6
The result of parsing would be
7
The result of semantic interpretation
8
The result of contextual/world knowledge
interpretation
9
Can also represent questionsWho loves Jane?
10
Parsing using Context-Free Grammars

• A bunch of rewrite rules
• 1. sentence ? noun_phrase verb_phrase 2.
  noun_phrase ? noun 3. noun_phrase ? article
  noun 4. verb_phrase ? verb 5. verb_phrase ?
  verb noun_phrase 6. article ? a 7. article ?
  the 8. noun ? man 9. noun ? dog10. verb ?
  likes11. verb ? bites

11
Parsing

• It is the search for a legal derivation of the
  sentence in hand starting with the nonterminal
  sentence.
• Sentence is the starting nonterminal.
• The result is a parse tree. A parse tree is a
  structure where each node is a symbol from the
  grammar. The root node is the starting
  nonterminal, the intermediate nodes are
  nonterminals, the leaf nodes are terminals.

12
The parse tree
13
Transition networks
14
The main idea

• Represent the rules in the grammar in the form
  of transition networks
• Then parsing a sentence is a matter of
  traversing the network
• If the label of the transition (arc) is a
  terminal, it must match the input, and the input
  pointer advances
• If the label of the transition (arc) is a
  nonterminal, the corresponding transition network
  is invoked recursively
• If several alternative paths are possible, each
  must be tried (backtracking)---very much like
  nondeterministic finite automaton---until a
  successful path is found

15
Parsing the sentence Dog bites.
16
Notes

• A successful parse is the complete traversal
  of the net for the starting nonterminal from
  sinitial to sfinal .
• If no path works, the parse fails. It is not a
  valid sentence.
• The following algorithm would be called using
  parse(sinitial )
• It would start with the net for sentence.

17
The algorithm

• Function parse(grammar_symbol)
• begin save pointer to current location in input
  stream case grammar_symbol is a terminal
  if grammar_symbol matches the next word in
  the input stream then return(success)
  else begin reset input stream
  return(failure) end
  grammar_symbol is a nonterminal begin
  retrieve the transition network labeled by
  grammar_symbol state start state of
  network if transition(state) returns
  success then return(success)
  else begin reset input stream
  return (failure) end endend.

18
The algorithm (contd)

• Function parse(grammar_symbol)
• begin save pointer to current location in input
  stream case grammar_symbol is a terminal
  if grammar_symbol matches the next word in
  the input stream then return(success)
  else begin reset input stream
  return(failure) end
  grammar_symbol is a nonterminal begin
  retrieve the transition network labeled by
  grammar_symbol state start state of
  network if transition(state) returns
  success then return(success)
  else begin reset input stream
  return (failure) end endend.

19
The algorithm (contd)

• Function transition(current_state)begin case
  current_state is a final state return
  (success) current_state is not a final
  state while there are unexamined
  transitions out of current_state do
  begin grammar_symbol the label on
  the next unexamined transition if
  parse(grammar_symbol) returns (success)
  then begin next_state state at
  the end of the transition if
  transition(next_state) returns (success)
  then return(success) end
  end return(failure) endend.

20
Grammars might be ambiguous
21
A different parse tree for the same sentence
22
The network may contain loops
adjective
Noun-phrase
noun
article
si
si
si
Traverse adjective twice to parse the noun
phrase the cute little puppy
23
Comments of transition networks

• They capture the regularity in the sentence
  structure
• They exploit the fact that only a small
  vocabulary is needed in a specific domain
• If a sentence doesnt make sense, it might be
  caught by the domain information. For instance,
  the answer to both of the following questions is
  there is none
• Pick up the blue cylinder
• Pick up the red blue cylinder