Scribd Logo
Upload

Welcome to Scribd!

  • 55 views

    Text Representation: Chengxiang "Cheng" Zhai Department of Computer Science University of Illinois at Urbana-Champaign

    Uploaded by

    Ayoub Bokhabrine
    This document discusses text representation and the types of analysis it enables. It presents multiple ways of representing text, from simple strings to more complex representations incorporating syntactic structures, entities, relations, and logic predicates. Higher-level representations require more human effort but allow deeper natural language processing and knowledge extraction. The course will focus on word-based representation, which is general, robust, requires little manual effort, and is powerful for many applications, though not all.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Text Representation: Chengxiang "Cheng" Zhai Department of Computer Science University of Illinois at Urbana-Champaign

    Uploaded by

    Ayoub Bokhabrine
    55 views5 pages
    This document discusses text representation and the types of analysis it enables. It presents multiple ways of representing text, from simple strings to more complex representations incorporating syntactic structures, entities, relations, and logic predicates. Higher-level representations require more human effort but allow deeper natural language processing and knowledge extraction. The course will focus on word-based representation, which is general, robust, requires little manual effort, and is powerful for many applications, though not all.

    Original Description:

    1-s2.0-S1877050915005402-main

    Original Title

    1-s2.0-S1877050915005402-main

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses text representation and the types of analysis it enables. It presents multiple ways of representing text, from simple strings to more complex representations incorporating syntactic structures, entities, relations, and logic predicates. Higher-level representations require more human effort but allow deeper natural language processing and knowledge extraction. The course will focus on word-based representation, which is general, robust, requires little manual effort, and is powerful for many applications, though not all.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    55 views5 pages

    Text Representation: Chengxiang "Cheng" Zhai Department of Computer Science University of Illinois at Urbana-Champaign

    Uploaded by

    Ayoub Bokhabrine
    This document discusses text representation and the types of analysis it enables. It presents multiple ways of representing text, from simple strings to more complex representations incorporating syntactic structures, entities, relations, and logic predicates. Higher-level representations require more human effort but allow deeper natural language processing and knowledge extraction. The course will focus on word-based representation, which is general, robust, requires little manual effort, and is powerful for many applications, though not all.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 5

    Text Representation

    ChengXiang “Cheng” Zhai


    Department of Computer Science
    University of Illinois at Urbana-Champaign

    1
    Text Representation
    5. Text-based prediction
    3. Topic mining & analysis

    Real World Observed World Text Data


    Perceive Express 1. Natural language
    processing & text
    (Perspective) (English) representation

    4. Opinion mining & 2. Word association


    sentiment analysis mining & analysis

    2
    A dog is chasing a boy on the playground String of characters

    A dog is chasing a boy on the playground Sequence of words


    Det Noun Aux Verb Det Noun Prep Det Noun + POS tags
    Noun Phrase Complex Verb Noun Phrase
    Noun Phrase
    Verb Phrase Prep Phrase + Syntactic structures
    Verb Phrase
    Sentence

    A dog A boy the playground


    CHASE ON + Entities and relations
    Animal Person Location

    Dog(d1). Boy(b1). Playground(p1). Chasing(d1,b1,p1). + Logic predicates

    Speech Act = REQUEST + Speech acts


    Closer to knowledge
    Deeper NLP: requires more human effort; less accurate representation 3
    Text Representation and Enabled Analysis
    This course

    Text Rep Generality Enabled Analysis Examples of Application


    String String processing Compression
    Words Word relation analysis; topic Thesaurus discovery; topic and
    analysis; sentiment analysis opinion related applications
    + Syntactic Syntactic graph analysis Stylistic analysis; structure-
    structures based feature extraction
    + Entities & Knowledge graph analysis; Discovery of knowledge and
    relations information network analysis opinions about specific entities
    + Logic Integrative analysis of scattered Knowledge assistant for
    predicates knowledge; logic inference biologists
    4
    Summary
    • Text representation determines what kind of mining algorithms can be
    applied
    • Multiple ways of representing text are possible
    – string, words, syntactic structures, entity-relation graphs,
    predicates…
    – can/should be combined in real applications
    • This course focuses on word-based representation
    – General and robust: applicable to any natural language
    – No/little manual effort
    – “Surprisingly” powerful for many applications (not all!)
    – Can be combined with more sophisticated representations
    5

    You might also like