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

Back-Translation_Sampling_by_Targeting_Difficult_Words_in_Neural_Machine_Translation.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=47 MARUYAMA
February 27, 2019
0
74

 Back-Translation_Sampling_by_Targeting_Difficult_Words_in_Neural_Machine_Translation.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=128

MARUYAMA

February 27, 2019
Tweet

More Decks by MARUYAMA

See All by MARUYAMA
vampire.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
69
Misspelling_Oblivious_Word_Embedding.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
52
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
62
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
61
20191028_literature-review.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
63
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
46
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
61
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
56
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
48

Featured

See All Featured
Testing 201, or: Great Expectations
A9704266587836f7e784235e5073b93e?s=48 jmmastey
21
5.4k
The Success of Rails: Ensuring Growth for the Next 100 Years
C44e1f7e22c3f23cff7bc130871047ef?s=48 eileencodes
3
510
Web Components: a chance to create the future
E190023b66e2b8aa73a842b106920c93?s=48 zenorocha
303
40k
How To Stay Up To Date on Web Technology
8081b26e05bb4354f7d65ffc34cbbd67?s=48 chriscoyier
780
250k
How GitHub Uses GitHub to Build GitHub
78b475797a14c84799063c7cd073962f?s=48 holman
465
280k
ピンチをチャンスに：未来をつくるプロダクトロードマップ #pmconf2020
E425fe9f170efa0dfaf8ab69d7107418?s=48 aki_i
21
14k
Building Applications with DynamoDB
39488f9d172ab92fd352f2cd7b73258d?s=48 mza
83
4.6k
The Language of Interfaces
Fde6c3a50ca518a909ef35c22c0ee0e4?s=48 destraynor
148
20k
GitHub's CSS Performance
64827b31aef81498662e8af4bd6d5157?s=48 jonrohan
1020
410k
It's Worth the Effort
Ba530e786553390f3fb271848485681c?s=48 3n
172
25k
StorybookのUI Testing Handbookを読んだ
50fc0fdc2327ecbe7350645812de52e3?s=48 zakiyama
4
2k
Fight the Zombie Pattern Library - RWD Summit 2016
9fa239b3154a0169d99ab7bf1422dd12?s=48 marcelosomers
226
15k

Transcript

  1. #BDL5SBOTMBUJPO4BNQMJOHCZ5BSHFUJOH%J⒏DVMU 8PSETJO/FVSBM.BDIJOF5SBOTMBUJPO .BS[JFI'BEBFFBOE$ISJTUPG.PO[ &./-1 QBHFTr -JUFSBUVSFSFWJFX /BHBPLB6OJWFSTJUZPG5FDIOPMPHZ5BLVNJ.BSVZBNB

  2. ֓ཁ ⾣຋༁ͷ࣭ͷ޲্ʹޮՌతͳٯ຋༁ͷαϯϓϦϯάख๏ͱ͸ʁ ⾣8.5OFXTUSBOTMBUJPOUBTLͰϥϯμϜαϯϓϦϯάͷ ٯ຋༁ʹൺ΂ɺ#-&6͕ %F&O  &O%F ޲্ ⾣໨తݴޠଆͰ༧ଌ͢Δͷ͕೉͍͠୯ޠΛத৺ʹɺ ٖࣅσʔλΛੜ੒͢Δख๏ΛఏҊ

  3. ٯ຋༁ʹΑΔσʔλ֦ு 4PVSDFTJEF 5BSHFUTJEF 1BSBMMFMDPSQVT 1BSBMMFMDPSQVT .POPMJOHVBM $PSQVT #BDLXBSE NPEFM 5SBJOJOH

  4. ٯ຋༁ʹΑΔσʔλ֦ு 4PVSDFTJEF 5BSHFUTJEF 1BSBMMFMDPSQVT 1BSBMMFMDPSQVT .POPMJOHVBM $PSQVT #BDLXBSE NPEFM

  5. ٯ຋༁ʹΑΔσʔλ֦ு 4PVSDFTJEF 5BSHFUTJEF 1BSBMMFMDPSQVT 1BSBMMFMDPSQVT .POPMJOHVBM $PSQVT #BDLXBSE NPEFM 4ZOUIFUJDEBUB

    (FOFSBUJPO

  6. ٯ຋༁ʹΑΔσʔλ֦ு 4ZOUIFUJDEBUB 4PVSDFTJEF 5BSHFUTJEF 1BSBMMFMDPSQVT 1BSBMMFMDPSQVT .POPMJOHVBM $PSQVT 'PSXBSE NPEFM

    5SBJOJOH

  7. ٯ຋༁ʹΑΔσʔλ֦ு 4ZOUIFUJDEBUB 5FTUEBUB 4PVSDFTJEF 5BSHFUTJEF 1BSBMMFMDPSQVT 1BSBMMFMDPSQVT .POPMJOHVBM $PSQVT 'PSXBSE

    NPEFM

  8. ٯ຋༁ʹΑΔσʔλ֦ு 4ZOUIFUJDEBUB 5FTUEBUB 4PVSDFTJEF 5BSHFUTJEF 1BSBMMFMDPSQVT 1BSBMMFMDPSQVT .POPMJOHVBM $PSQVT 3FTVMU

    'PSXBSE NPEFM

  9. ͸͡Ίʹ ⾣Ұൠతʹɺʮٯ຋༁ʹΑΔσʔλ֦ு͸ɺPWFSpUUJOH΍ ྲྀெੑͷ໰୊Λܰݮ͢ΔʯͱݴΘΕ͍ͯΔ ⾣ϙΠϯτ͸ɺʮͲͷΑ͏ͳσʔλΛ༻͍֦ͯுΛߦ͏͔ʯ

  10. ⾣ςετσʔλͱυϝΠϯ͕ྨࣅ͢ΔσʔλΛબ୒ͭͭ͠ ϞσϧΛֶशͤ͞Δ͜ͱͰੑೳΛվળ ؔ࿈ݚڀ ⾣ٯ຋༁ʹ͓͚ΔɺυϝΠϯʹج͍ͮͨσʔλબ୒͸ɺ ϥϯμϜαϯϓϦϯάͱൺ΂ͯେࠩͳ͠ WBOEFS8FFTFUBM 1IBNFUBM

  11. ⾣ٖࣅσʔλ௥Ճલޙʹ͓͚Δɺ༧ଌଛࣦͷมԽΛௐࠪ ٯ຋༁ͱτʔΫϯ༧ଌ "UUFOUJPOCBTFEFODPEFSEFDPEFSNPEFM ϥϯμϜαϯϓϦϯάʹΑΔٯ຋༁Ͱٙࣅσʔλੜ੒

  12. ٯ຋༁ͱτʔΫϯ༧ଌ ٖࣅσʔλ௥ՃʹΑΔ ༧ଌଛࣦͷ૿ݮ ໨తݴޠଆͷ୯ޠස౓ ର਺

  13. ٯ຋༁ͱτʔΫϯ༧ଌ ٖࣅσʔλ௥ՃʹΑΔ ༧ଌଛࣦͷݮগ͸ CBTFMJOFQSFEJDUJPOMPTT ͕ߴ͍୯ޠͰൃੜ͢Δ ʮ༧ଌ͕ࠔ೉ʯͳ΋ͷΛ ٙࣅσʔλʹՃ͑ͨํ͕ ޮՌతʁ

  14. ༧ଌࠔ೉ͳτʔΫϯʹجͮ͘αϯϓϦϯά ⾣ʮ༧ଌ͕ࠔ೉ʯͳ΋ͷΛͲͷΑ͏ʹαϯϓϦϯά͢Δ͔ʁ ස౓ͷᮢ஋ ༧ଌଛࣦͷฏۉͷᮢ஋ ༧ଌଛࣦͷඪ४ภࠩͷᮢ஋ 1SFEJDUJPOMPTTͷൺ཰ʹ߹ΘͤͯαϯϓϦϯά

  15. ༧ଌࠔ೉ͳτʔΫϯʹجͮ͘αϯϓϦϯά

  16. จ຺ʹجͮ͘αϯϓϦϯά ⾣ಉ͡τʔΫϯͰ΋ʮ༧ଌͷࠔ೉͞ʯ͸จ຺ʹΑͬͯҟͳΔ ⾣ྨࣅͨ͠จ຺Λ΋ͭ৔߹͸ɺͦͷτʔΫϯͷ༧ଌͷࠔ೉͞ ʹ͍ͭͯ΋ྨࣅ͍ͯ͠ΔͱԾఆ ⾣ʮ༧ଌͷࠔ೉͞ʯ ʮจ຺ͷྨࣅੑʯͰαϯϓϦϯά

  17. จ຺ʹجͮ͘αϯϓϦϯά ⾣lจ຺zͷఆٛ /FJHICPSJOHUPLFOT 50,&/4 /FJHICPSJOHTVCXPSEVOJUT 4803%4 

  18. จ຺ʹجͮ͘αϯϓϦϯά ⾣lྨࣅ౓zͷܭࢉํ๏ .BUDIJOHUIFMPDBMDPOUFYU ."5$) 8PSESFQSFTFOUBUJPOT &.#  7 ɾ จ຺಺ͷ֤τʔΫϯͷ୯ޠϕΫτϧͷฏۉ

  19. จ຺ʹجͮ͘αϯϓϦϯά

  20. ·ͱΊ ⾣຋༁ͷ࣭ͷ޲্ʹޮՌతͳٯ຋༁ͷαϯϓϦϯάख๏ͱ͸ʁ ⾣໨తݴޠଆͰ༧ଌ͢Δͷ͕೉͍͠୯ޠΛத৺ʹɺ ٖࣅσʔλΛੜ੒͢Δख๏ΛఏҊ ⾣8.5OFXTUSBOTMBUJPOUBTLͰϥϯμϜαϯϓϦϯάͷ ٯ຋༁ʹൺ΂ɺ#-&6͕ %F&O  &O%F ޲্

  21. ࢀߟจݙ <>/HPD2VBO1IBN +BO/JFIVFT 5IBOI-F)B &VOBI$IP .BUUIJBT4QFSCFS BOE "MFYBOEFS8BJCFM5IFLBSMTSVIFJOTUJUVUFPGUFDIOPMPHZTZTUFNTGPSUIFOFXT USBOTMBUJPOUBTLJOXNU*O1SPDFFEJOHTPGUIF4FDPOE$POGFSFODFPO.BDIJOF 5SBOTMBUJPO

    QBHFTr <>.BSMJFTWBOEFS8FFT "SJBOOB#JTB[[B BOE$ISJTUPG.PO[%ZOBNJDEBUB TFMFDUJPOGPSOFVSBMNBDIJOFUSBOTMBUJPO*O1SPDFFEJOHTPGUIF$POGFSFODFPO &NQJSJDBM.FUIPETJO/BUVSBM-BOHVBHF1SPDFTTJOH QBHFTr $PQFOIBHFO  %FONBSL"TTPDJBUJPOGPS$PNQVUBUJPOBM-JOHVJTUJDT