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

SNLP2019: Improving Neural Conversational Model...

Reina Akama
September 28, 2019
680

SNLP2019: Improving Neural Conversational Models with Entropy-Based Data Filtering

Reina Akama

September 28, 2019
Tweet

Transcript

  1. Improving Neural Conversational Models with Entropy-Based Data Filtering Richard Csaky,

    Patrik Purgai, Gabor Recski ACL2019 ˞ਤද͸࿦จΑΓҾ༻ ಡΉਓ: ੺ؒ ྯಸ (౦๺େ/ཧݚAIP) ୈ11ճ࠷ઌ୺NLPษڧձ 2019-09-28
  2. ·ͱΊ • ໨త: ଟ༷ੑͷ͋ΔԠ౴Λੜ੒͢Δ • ઓུ: Ϟσϧʹ generic ͳԠ౴Λֶशͤ͞ͳ͍ •

    ఏҊ: ֶशϖΞσʔλϑΟϧλϦϯά • ൃ࿩ͷ൚༻ੑΛ entropy Ͱදݱ • Entropy ͷߴ͍ൃ࿩Λֶशσʔλ͔Βআڈ • ධՁ: • ର࿩Ԡ౴ੜ੒λεΫ • ෳ਺ࣗಈධՁई౓ͰείΞ޲্ͷ܏޲ 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ 
  3. ର࿩Ԡ౴ੜ੒ͰΑ͋͘Δ࿩ 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ  ೖྗ: What color is the sky?

    ग़ྗ: I don’t know. ೖྗ: What is your name? ग़ྗ: I don’t know. ೖྗ: I’m losing my key. ग़ྗ: I don’t know. ೖྗ: Hey! What's up!? ग़ྗ: I don’t know what you are talking about.
  4. ͳͥ generic ͳԠ౴͕ੜ੒͞ΕΔʁ • ର࿩͸ many-to-many ͳੑ࣭Λ࣋ͭ • χϡʔϥϧϞσϧ͸ฏۉΛֶश͢Δ [Wu+’18]

    “ؒҧΘͳ͍” “҆શͳ” Ԡ౴΁ 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ  Wu+’18; Why do neural response generation models prefer universal replies? arXiv:1808.09187 What color is the sky? It is blue. The setting sun is amazingly red. I don’t know. what do you mean? I like orange better. You look hot.
  5. Many-to-many ͷղܾΞϓϩʔν Ϟσϧ • Ϟσϧ֦ு [Serban+’17; Zhao+’18; Gao+’19; Wang+’18] •

    જࡏม਺ΛαϯϓϦϯάɾσίʔυΛվળ • ଛࣦؔ਺ [Li+’16] • ڧԽֶशɾఢରతֶश [Li+’16; Serban+’17; Lipton+’18] σʔλ • ෇Ճ৘ใͷར༻ [Li+’16; Liu+’17; Xing+’18; Baheti+’18] • ର࿩ཤྺɾΧςΰϦʢe.g., ϖϧιφɾײ৘ɾτϐοΫɾ஌ࣝʣ • ֶशσʔλϑΟϧλϦϯά 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ 
  6. ఏҊ: Entropy-based training data filtering Entropy ͕ߴ͍ൃ࿩Λֶशσʔλ͔Βআڈ 1. SOURCE: 2.

    TARGET: 3. BOTH: SOURCE or TARGET 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ  > 1 > 1
  7. ࣮ݧ: ର࿩Ԡ౴ੜ੒ • ֶशσʔλ: DailyDialog (90k utterances in 13k dialogs)

    • Ϟσϧ: Transformer [Vaswani+’17] • ධՁ: ࣗಈධՁई౓ (17छ) • Word and utterance entropy [Serban+’17] • KL divergence • Embedding metrics (average, extrema, greedy) • Coherence • Distinct • BLEU 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ  Entropy-based training data filtering  (proposed) vs  (base) Ϋϥελߟྀ
  8. ࣮ݧ݁Ռ: Filtering ༗ > ແ 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ  • TARGET

    ϑΟϧλϦϯά͕࠷ྑͷ݁Ռ Random Gold (Table 2) non-genericness diversity
  9. ·ͱΊ • ໨త: ଟ༷ੑͷ͋ΔԠ౴Λੜ੒͢Δ • ઓུ: Ϟσϧʹ generic ͳԠ౴Λֶशͤ͞ͳ͍ •

    ఏҊ: ֶशϖΞσʔλϑΟϧλϦϯά • ൃ࿩ͷ൚༻ੑΛ entropy Ͱදݱ • Entropy ͷߴ͍ൃ࿩Λֶशσʔλ͔Βআڈ • ධՁ: • ର࿩Ԡ౴ੜ੒λεΫ • ෳ਺ࣗಈධՁई౓ͰείΞ޲্ͷ܏޲ 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ 
  10. +α: Best performance ͸Ͳ͜ʁ 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ  • valid loss

    ࠷௿ (10-20k) < training loss ࠷௿ (80-100k) | , | '- '. distinct 567
  11. +α: Utterance cluster Λߟྀ • ྨࣅൃ࿩ΛΫϥελԽ • AVG-EMBEDDING (AE) •

    SENT2VEC (SC) • ݁Ռɿfiltering ແ < AE,SC < ID (ඇΫϥελԽ) • tab. 1 • tab. 2 2019-09-28 ୈ11ճ࠷ઌ୺NLPษڧձ