• Share
  • Email
  • Embed
  • Like
  • Save
  • Private Content
Semantic Analysis: theory, applications and use cases
 

Semantic Analysis: theory, applications and use cases

on

  • 4,104 views

Presentation we gave at 6th Seminar of Finnish-Russian University Cooperation in Telecommunications (FRUCT) Program organized by Nokia Research Center, Helsinki University of Technology, ...

Presentation we gave at 6th Seminar of Finnish-Russian University Cooperation in Telecommunications (FRUCT) Program organized by Nokia Research Center, Helsinki University of Technology, Saint-Petersburg State University of Aerospace Instrumentation and sponsored by Nokia Siemens Networks, IEEE Russia (North West) Section, Nokia University Cooperation Program in Russia

www.fruct.org

Statistics

Views

Total Views
4,104
Views on SlideShare
2,917
Embed Views
1,187

Actions

Likes
0
Downloads
36
Comments
0

5 Embeds 1,187

http://semanticanalyzer.info 1149
http://dmitrykan.blogspot.com 19
http://www.slideshare.net 12
http://dmitrykan.blogspot.fi 6
http://dmitrykan.blogspot.co.at 1

Accessibility

Categories

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

    Semantic Analysis: theory, applications and use cases Semantic Analysis: theory, applications and use cases Presentation Transcript

    • Semantic analysis: theory,  applications and use cases 6th Seminar of FRUCT Dmitry Kan, Vladimir Poroshin Helsinki, 2009
    • Road map • Math model of a Natural Language (NL) • Three levels of text analysis • Semantics vs syntax • Applications • Use cases
    • Math model of a Natural Language • Backbone of NL: verbs + prepositions • Verb = F(arg1, …, argn) • Prepositions: 3D space (behind), time space (during), cause‐and‐effect relation (due to) • Class hierarchy (=world picture) • Basis functions • Words adjunction
    • Math model: basis functions • Caus(x,y) = x causes y • Cont(x) = x continues • Hab(x,y) = x has y • Incep(x) = x begins • Oper(x,y) = x performs y • Lab(x,y) = x under action of y • Prepar(x) = prepare x, x is prepared • Fin(x) = x finishes, stops
    • Math model: examples • Caus(Subj, Fin Lab(Accus, FIRE)) = to  extinguish a fire (=cause to stop having Subj  under action of fire) • Caus(Subj, Prepar(FOOD Accus)) = to stew the  vegetables (cause the Subj to get cooked) • Both examples map to the same Russian verb  ”тушить” => semantic disambiguation
    • Road map • Math model of a NL • Three levels of text analysis • Semantics vs syntax • Applications • Use cases
    • Three levels of analysing text • Morphological analysis: word level • Syntactic and semantic analysis: sentence  level • Object properties and relationships, anaphora  resolution: text level • Sentence = P(f1(x1,…,xn),…,fn(x1,…,xn)) – superposition of functions
    • Three levels of analysing text Machinese Syntax is a syntactic parser that returns base forms and  compound structure, produces part‐of‐speech classes, inflectional  tags, noun phrase markers and syntactic dependencies.
    • Road map • Math model of a NL • Three levels of text analysis • Semantics vs syntax • Applications • Use cases
    • Semantics vs syntax • Он пришёл из вежливости (He came out of  courtesy) WHY? • Из (вежливость) generates ”WHY?” • Он пришёл из деревни (He came from a  village) WHERE FROM? • Из(деревня) generates ”WHERE FROM?”
    • Road map • Math model of a NL • Three levels of text analysis • Semantics vs syntax • Applications • Use cases
    • Applications • Intellectual search systems • Question‐answering systems • Spell checker • Summarization • Sentiment analysis • Machine Translation • Knowledge base • Facts extraction
    • Road map • Math model of a NL • Three levels of text analysis • Semantics vs syntax • Applications • Use cases
    • Use cases • Smart street dating: semantic search of the  best matching candidates around you • FAQ mobile agent: automatically suggest  solutions to the support requests • Sentiment recognition: goods evaluation • Automatic summarization: limit  information load on mobile devices
    • References [1]Tuzov V. A.: Computer semantics of Russian language. Saint‐ Petersburg University Press, Saint‐Petersburg, 2004 (in  Russian). [2]Kan D. A., Lebedev I.S.: Method of formalizing semantical links  between objects in a natural language text. Bulletin of Saint‐ Petersburg University. Series 10. 2008. Issue 2. pp 56‐61 (in  Russian). [3]Kan D. A.: Method for automatic creation of translational  semantic dictionary for Machine Translation // XL Conference  Control Processes and Stability'09, pp. 429‐435 (in Russian). [4] www.semanticanalyzer.info
    • Questions
    • Thank you!