AutoTutor Authoring Tool

Document Sample
AutoTutor Authoring Tool Powered By Docstoc
					Two Related Lexico-Syntactic
 Approaches to Entailment

                Vasile Rus

      Institute for Intelligent Systems
     Department of Computer Science
           TODAY- Outline
• General strategy
  – Map T and H into lexico-syntactic graphs
  – Perform graph subsumption between graph-T and
  – Additive strategy
     • Not cascaded
• Two approaches
  – Lexico-syntactic approach
  – Dependency-based approach
• Results, Comparison, Conclusions
          The Two Approaches
• Lexico-syntactic approach
  –   Lexical component
  –   Syntactic component
  –   Dependencies derived from phrase-based parse trees
  –   Negation
  –   thesaurus
• Dependency-based approach
  – Dependencies from MINIPAR
  – Lexical component by default
  – Postprocessing (thanks to Vivi Nastase)
       • To eliminate unused information
       • To retain only dependencies among content words
        Graph Subsumption
• Map nodes and edges in H-graph to nodes
  and edges in T-graph
• complex mapping based on
  – Named Entity Inferences: Overture Services
    Inc -- Overture
  – Word-level entailment / equivalence: take
    over – buy
  – Syntactic Info:
    • Yahoo is the agent of buying
      From Sentences to Graph
• vertices represent content words
• edges represent dependencies
  – local dependencies (intra-phrase) are
    straightforwardly obtained from a parse tree
  – remote dependencies are obtained using an
    extended functional tagger
  – Or from MINIPAR (for the second approach)
         The Entailment Score
•The score is so defined to be non-reflexive:
   entail(T, H) ≠ entail(H,T)

      Score is also used as confidence
           The Parameters
• the following parameters worked best on
  α=.5 β =.5 γ=0
• Explicit
   – Clue phrases
      • no, not, neither … nor
      • shortened forms: „nt
• Implicit
   – Antonymy in WordNet
• Hypothetical sentences:
              “a possible visit by Clinton to China”
                   does not entail
               “Clinton visited China”
   – a form of negation
      Results – Lexico-Syntactic

System             Accuracy Average precision
Lexico-syntactic   0.5900   0.6047
Lex                0.5663   0.5823
Lex-cnt-words      0.5875   0.5725
Lex+syn            0.5737   0.5841
Lex+syn+neg        0.5800   0.6096
Lex+syn+synt       0.5813   0.5941
lex+syn+synt+neg 0.5900     0.6047

System             Accuracy Average precision
Lexico-syntactic   0.5900   0.6047
Lex+syn+synt       0.5813   0.5941

Dependency-based   0.5837   0.5785
• Lexical information significantly helps
• The other components (synonymy,
  dependencies, negation) add value but not
         Missed Opportunities
• Linguistic Level
  – Five = 5
  – Tuscany province = province of Tuscany
• Current subsumption algorithm is weak
     • T: Besancon is the capital of France‟s watch and clock-
       making industry and of high precision engineering.
     • H: Besancon is the capital of France.
    Solution: matching with more complex
• World Knowledge
          More Conclusions
• Our system is light
  – Good for interactive environment such as
    Intelligent Tutoring Systems
• No training involved
  – Just development to tune few parameters
       One More Conclusion
• It is not clear whether there is a difference
  among the two ways to obtain
Two Related Lexico-Syntactic
 Approaches to Entailment

       Thank you everyone !

Shared By: