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

Learning to compose neural networks for question answering

himkt
July 10, 2016

Learning to compose neural networks for question answering

Andreas, Jacob, et al. "Learning to compose neural networks for question answering." arXiv preprint arXiv:1601.01705 (2016).

This is the presentation material used in journal club at University of Tsukuba, Kasuga (2016/07/16)

himkt

July 10, 2016
Tweet

More Decks by himkt

Other Decks in Science

Transcript

  1. Overview - 1. Network Layout • ࣭໰จΛ܎Γड͚ղੳʢStanford Dependency Parserʣ •

    ܎Γड͚݁Ռʹ΋ͱ͍ͮͯऔΓ͏ΔωοτϫʔΫߏ଄ͷ ީิΛྻڍ • ࣭໰จΛॴ༩ͱͨ͠ࡍͷωοτϫʔΫʹؔ͢Δ৚݅෇͖ ֬཰ΛධՁͯ͠ωοτϫʔΫΛܾఆ
  2. Module inventory • 6छྨͷϞδϡʔϧͱݺ͹ΕΔؔ਺ • Attention͔LabelΛग़ྗ͢Δ • Attention: pixels •

    Label: true/false or lexicon (e.g. “bird”) • ֤Ϟδϡʔϧ͸ग़ྗͱҾ਺ʹؔͯ͠ʮܕʯ੍໿Λ࣋ͭ • Lookup :: input -> Attention • Find :: input -> Attention • Relate :: Attention -> Attention • And :: Attention* -> Attention • Describe :: Attention -> Labels • Exists :: Attention -> Labels
  3. Produce an answer • What color is the bird? ->

    (describe[color] find[bird]) -> black and white (lexicon) • Are there any states? -> (exists find[state]) -> true
  4. Components • Layout model • ωοτϫʔΫߏ଄Λਪఆ͢Δ • Execution model •

    ճ౴Λੜ੒͢Δ • Training • ;ͨͭͷύϥϝʔλΛಉ࣌ʹֶश • ڧԽֶश p(z|x; l ) pz (y|w; e )
  5. Layout Model • ৚͖݅ͭ֬཰͸ιϑτϚοΫεͷग़ྗ • ͨͩ͠ɼ • ɹɹɹɹɹɹɹ͸ύϥϝʔλ • ɹɹɹ͸LSTMͷग़ྗ

    • ɹɹɹ͸ɹ ʢi൪໨ͷީิͷωοτϫʔΫʣͷ embedding? ʢfeature vectorʣ p(zi |x; l) = es(zi |x) n j=1 es(zj |x) s(zi |x) = aT (Bhq (x) + Cf(zi ) + d) l = (a, B, C, d) hq (x) f(zi ) zi
  6. Training • ڧԽֶश • ɹΛɹɹɹɹɹ͔ΒαϯϓϦϯά • ωοτϫʔΫ͕ܾఆͨ͠ΒɹɹɹɹɹɹɹΛ
 ௚઀࠷େԽͯ͠ɹɹΛߋ৽ • Policy

    Gradient MethodʹΑΓɹ Λߋ৽ • ޯ഑ɿɹɹɹɹɹɹɹɹɹɹɹɹɹɹʢɹ͸ใुʣ z p(z|x; l ) log p(y|z, x, e ) e l J( l ) = E log p(z|x; l ) · r r J( l ) = E log p(z|x; l ) log p(y|z, w; e )
  7. Experimental result • VisualQAʢTable 1ʣͱGeoQAʢTable 2ʣͰstate-of-the-art • VisualQA: images •

    GeoQAɿstructured domains • ෳ਺ͷ࣭໰Ԡ౴λεΫʹରԠͰ͖Δ͜ͱ͕ূ໌͞Εͨ