Contextual Analysis for the Representation of Words

Dat HUYNH, Dat TRAN, Wanli MA

    Research output: Contribution to journalArticle

    4 Citations (Scopus)

    Abstract

    Building the representation of word meanings is one of the key challenges in many language-based applications from document understanding, text summarization to sentiment analysis. One of the reasons to make this task harder is that word meanings involve not only the word surfaces in contexts, but the human experiences in specific domains. Previous work in the field considers these issues separately by analysing text contents in one hand and dealing with knowledge-based information on the other hand. In this work, we address this issue by accumulating contextual information of words and knowledge-based contents to construct the representation of words. We evaluate the effectiveness of the representation via the task of semantic similarity on standard benchmarks. The experimental results show the strong correlation between the proposed word representation to the perception of human in the task of semantic similarity measure.

    Original languageEnglish
    Pages (from-to)148-152
    Number of pages5
    JournalIAENG International Journal of Computer Science
    Volume41
    Issue number2
    Publication statusPublished - 2014

    Fingerprint

    Semantics

    Cite this

    @article{7384c67ce98d4042bc65eff63040c8cd,
    title = "Contextual Analysis for the Representation of Words",
    abstract = "Building the representation of word meanings is one of the key challenges in many language-based applications from document understanding, text summarization to sentiment analysis. One of the reasons to make this task harder is that word meanings involve not only the word surfaces in contexts, but the human experiences in specific domains. Previous work in the field considers these issues separately by analysing text contents in one hand and dealing with knowledge-based information on the other hand. In this work, we address this issue by accumulating contextual information of words and knowledge-based contents to construct the representation of words. We evaluate the effectiveness of the representation via the task of semantic similarity on standard benchmarks. The experimental results show the strong correlation between the proposed word representation to the perception of human in the task of semantic similarity measure.",
    keywords = "Contextual-analysis, Word-representation, Wikipedia",
    author = "Dat HUYNH and Dat TRAN and Wanli MA",
    year = "2014",
    language = "English",
    volume = "41",
    pages = "148--152",
    journal = "IAENG International Journal of Computer Science",
    issn = "1819-656X",
    publisher = "International Association of Engineers",
    number = "2",

    }

    Contextual Analysis for the Representation of Words. / HUYNH, Dat; TRAN, Dat; MA, Wanli.

    In: IAENG International Journal of Computer Science, Vol. 41, No. 2, 2014, p. 148-152.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Contextual Analysis for the Representation of Words

    AU - HUYNH, Dat

    AU - TRAN, Dat

    AU - MA, Wanli

    PY - 2014

    Y1 - 2014

    N2 - Building the representation of word meanings is one of the key challenges in many language-based applications from document understanding, text summarization to sentiment analysis. One of the reasons to make this task harder is that word meanings involve not only the word surfaces in contexts, but the human experiences in specific domains. Previous work in the field considers these issues separately by analysing text contents in one hand and dealing with knowledge-based information on the other hand. In this work, we address this issue by accumulating contextual information of words and knowledge-based contents to construct the representation of words. We evaluate the effectiveness of the representation via the task of semantic similarity on standard benchmarks. The experimental results show the strong correlation between the proposed word representation to the perception of human in the task of semantic similarity measure.

    AB - Building the representation of word meanings is one of the key challenges in many language-based applications from document understanding, text summarization to sentiment analysis. One of the reasons to make this task harder is that word meanings involve not only the word surfaces in contexts, but the human experiences in specific domains. Previous work in the field considers these issues separately by analysing text contents in one hand and dealing with knowledge-based information on the other hand. In this work, we address this issue by accumulating contextual information of words and knowledge-based contents to construct the representation of words. We evaluate the effectiveness of the representation via the task of semantic similarity on standard benchmarks. The experimental results show the strong correlation between the proposed word representation to the perception of human in the task of semantic similarity measure.

    KW - Contextual-analysis

    KW - Word-representation

    KW - Wikipedia

    UR - http://www.scopus.com/inward/record.url?scp=84901507332&partnerID=8YFLogxK

    M3 - Article

    VL - 41

    SP - 148

    EP - 152

    JO - IAENG International Journal of Computer Science

    JF - IAENG International Journal of Computer Science

    SN - 1819-656X

    IS - 2

    ER -