Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment

himkt
September 26, 2016

Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in Distributional Vectors for Lexical Entailment

春日エリア読み会(2016/09/26)

himkt

September 26, 2016
Tweet

More Decks by himkt

Other Decks in Science

Transcript

  1. Relations such as Hypernymy: Identifying and Exploiting Hearst Patterns in

    Distributional Vectors for Lexical Entailment [email protected] ಡΈձ @ य़೔ΤϦΞ <2016/09/26> * ਤ͸ຊจ͔ΒҾ༻
  2. ؚҙؔ܎ • ೋͭͷจ T (text) ͱ H (hypothesis) ͕͋Δͱ͖ɼ
 T

    ͕ਖ਼͍͠ -> H ΋ਖ਼͍͠ͱਪ࿦Ͱ͖Δ ೣ͸ಈ෺ ੢දϠϚωί͸ಈ෺
  3. ৭ʑͳσʔληοτ -&%4
 ʢۉߧσʔλʣ 8PSE/FU͔Β࡞ΒΕͨσʔλ ϖΞͣͭ  ਖ਼ྫ্ҐԼҐؔ܎ͷ୯ޠϖΞ ෛྫ্ҐԼҐؔ܎Ͱ͸ͳ͍୯ޠϖΞ SBOEPNTBNQMF #-&44


    ʢෆۉߧσʔλʣ छྨͷΧςΰϦ͔Βબ୒͞Εͨݸͷ໊ࢺ ໊֤ࢺɿԼҐޠɾ্Ґޠɾ෦෼ޠɾద౰ͳޠ ϥϯμϜ  ্ҐԼҐؔ܎Λਖ਼ྫɼͦΕҎ֎ͷؔ܎Λෛྫͱͯ͠ѻ͏ .FEJDBM
 ʢෆۉߧσʔλʣ XPSEWFSCPCKFDU ͷࡾͭ૊σʔλ ݅  ؚҙʹؔ͢Δσʔλ͸݅ ༷ʑͳޠኮؔ܎ΛؚΈɼ೉͍͠ 5. ʢۉߧσʔλʣ ޠኮؔ܎σʔλʢؚ݅ҙؔ܎͸݅ʣ
  4. ConcatϞσϧৄ͘͠ Linear (hH, wi) = ˆ pT hH, wi =

    h ˆ H, ˆ wiT hH, , wi = ˆ HT H + ˆ wT w
  5. ConcatϞσϧৄ͘͠ Linear (hH, wi) = ˆ pT hH, wi =

    h ˆ H, ˆ wiT hH, , wi = ˆ HT H + ˆ wT w
  6. ConcatϞσϧৄ͘͠ Linear (hH, wi) = ˆ pT hH, wi =

    h ˆ H, ˆ wiT hH, , wi = ˆ HT H + ˆ wT w ʊਓਓਓਓਓਓਓਓਓਓਓਓʊ ʼɹ୯ޠؒͷؔ܎Ψϯແࢹɹʻ ʉY^Y^Y^Y^Y^Y^Y^Y^Y^Y^Yʉ
  7. ·ͱΊ • ޠኮؔ܎Λਪఆ͢ΔλεΫʹؔ͢Δݚڀ • طଘͷ͍͔ͭ͘ͷओཁͳϞσϧɾσʔληοτͷ෼ੳ • ಛʹConcat Modelʹ஫໨ • Concat

    Model͸Hearst PatternΛݕ஌͢ΔΑ͏ͳ
 ֶशΛ͍ͯͨ͠ • ͜ͷৼΔ෣͍ͱɼ୯ޠؒͷྨࣅ౓ɼ
 ͦͯ͠Inclusion HypothesisΛૉੑͱͨ͠ϞσϧΛఏҊ • ෳ਺ͷλεΫͰstate-of-the-artΛୡ੒ͨ͠
  8. ࢀߟจݙ 1. Hearst, Marti A. "Automatic acquisition of hyponyms from

    large text corpora." Proceedings of the 14th conference on Computational linguistics-Volume 2. Association for Computational Linguistics, 1992. 2. Levy, Omer, et al. "Do supervised distributional methods really learn lexical inference relations." Proceedings of NAACL, Denver, CO (2015).