スピンモデルによる単語の感情極性抽出  [in Japanese] Extracting Semantic Orientations Using Spin Model  [in Japanese]

Access this Article

Search this Article

Author(s)

Abstract

単語の感情極性(望ましいか否か)を判定する方法を提案する.提案手法では,単語の感情極性を電子のスピンの方向と見なし,語釈文,シソーラス,コーパスによって構築された語彙ネットワークをスピン系でモデル化する.平均場近似を利用してスピン系の状態を近似的に求めることにより,単語の感情極性を判定する.また,系の状態に影響を与えるハイパーパラメータの予測方法も同時に提案する.提案手法を用いてWordNet に収録されている語彙に対して実験を行い,14 語という少数の単語を種とした場合は約80%の正解率で,3 000We propose a method for extracting semantic orientations of words: desirable or undesirable. We construct a lexical network out of glosses in a dictionary, a thesaurus and a corpus. Regarding semantic orientations of words on the network as spins of elect

We propose a method for extracting semantic orientations of words : desirable or undesirable. We construct a lexical network out of glosses in a dictionary, a thesaurus and a corpus. Regarding semantic orientations of words on the network as spins of electrons, we use the mean field approximation to compute the approximate probability function of the system instead of the intractable actual probability function and determine the semantic orientations of words. We also propose a criterion for hyper-parameter selection. We conducted experiments with English lexicon in WordNet and obtained approximately 80% accuracy with 14 seed words and approximately 90% accuracy with about 3,000 seed words.

Journal

  • IPSJ journal  

    IPSJ journal 47(2), 627-637, 2006-02-15 

    Information Processing Society of Japan (IPSJ)

References:  26

You must have a user ID to see the references.If you already have a user ID, please click "Login" to access the info.New users can click "Sign Up" to register for an user ID.

Cited by:  16

You must have a user ID to see the cited references.If you already have a user ID, please click "Login" to access the info.New users can click "Sign Up" to register for an user ID.

Codes

  • NII Article ID (NAID)
    110004081271
  • NII NACSIS-CAT ID (NCID)
    AN00116647
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    1882-7764
  • NDL Article ID
    7839141
  • NDL Source Classification
    ZM13(科学技術--科学技術一般--データ処理・計算機)
  • NDL Call No.
    Z14-741
  • Data Source
    CJP  CJPref  NDL  IPSJ 
Page Top