Presentation is loading. Please wait.

Presentation is loading. Please wait.

74.406 Natural Language Processing - Feature Structures - Feature Structures and Unification.

Similar presentations


Presentation on theme: "74.406 Natural Language Processing - Feature Structures - Feature Structures and Unification."— Presentation transcript:

1 74.406 Natural Language Processing - Feature Structures - Feature Structures and Unification

2 Feature Structures, Grammar, Parsing Feature Structures describe additional syntactic-semantic information, like category, person, number, e.g.goes  specify feature structure constraints (agreements) as part of the grammar rules during parsing, check agreements of feature structures (unification) example S  NP VP =

3 Feature Structures, Grammar, Parsing Feature Structures describe additional syntactic-semantic information, like category, person, number, e.g.goes  specify feature structure constraints (agreements) as part of the grammar rules during parsing, check agreements of feature structures (unification) example S  NP VP =

4 Feature Structures Feature structures describe linguistic attributes or features like number, person associated with words or syntactic constituents like noun phrase. Feature structures are sets of features and values, e.g. hat[Numbersing ] buys[Person 3 ] [Numbersing ]

5 Feature Structures - Agreement Feature structures can be collected in one ‘variable’ called agreement. buys agreement [Person 3] [Number sing] Often these feature structures are referenced through an identifier.

6 Feature Structures as Constraints Ungrammatical expressions like He go...or We goes... One scarf... He sleeps the book... can be excluded using feature constraints. Feature structures are used to describe grammatical attributes of the respective item (word, syntactic category, phrase) like number, person,... and connections between them (constraints), which are checked during processing (unification). example S  NP VP = =

7 Add to feature structure the syntactic category cat: buys cat verb agreement [Person 3 ] [Number sing] Feature Structures and Categories

8 Compare and combine feature structures: he buys buys cat verb agreement [Person 3 ] [Number sing] he cat noun agreement [Person 3 ] [Number sing] Feature Structures and Unification 1

9 S → NP VP = = buys cat verb agreement [Person 3 ] [Number sing] he cat noun agreement [Person 3 ] [Number sing] Using Feature Structures must match in unification

10 Unification of Feature Structures Agreement is checked by the unification operation and merged feature structure is determined according to the following cases: [feature i value i ] |_| [feature i value i ] = [feature i value i ] [feature i value i ] |_| [feature i value k ] = fail if value i  value k [feature i value i ] |_| [feature i undef.] = [feature i value i ] [feature i value i ] |_| [feature k value k ] = feature i value i feature k value k if feature i  feature k

11 "Inheritance" of Feature Structures Feature structures are "inherited" during parsing or generation, using the feature structure of the head of a phrase: NP  det Nom NP i=1,..,n  det Nom i=1,..,n Nom i=1,..,n  pre-Nom Nom i=1,..,n post-Nom Complex feature structures are often referenced through identifying numbers. Constraints on feature structures can be checked using these references; and the same feature structure can be used in different parts of the parse tree through reference. head

12 Features and Subcategorization NP modifiers or Verb complements head noun + modifiers + agreement head verb + complements + agreements “... the man who chased the cat out of the house...” “... the man chased the barking dog who bit him...” Agreements are passed on / inherited within phrases, e.g. agreement of VP derived from Head-Verb of VP: determined by

13 References D. Jurafsky & J. H. Martin, Speech and Language Processing, Prentice-Hall, 2000. (Chapters 9 and 10) J. Eisner, 600.465 - Intro to NLP, Department of Computer Science, Johns-Hopkins University http://cs.jhu.edu/~jason http://cs.jhu.edu/~jason


Download ppt "74.406 Natural Language Processing - Feature Structures - Feature Structures and Unification."

Similar presentations


Ads by Google