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

Back-Translation_Sampling_by_Targeting_Difficul...

Avatar for MARUYAMA MARUYAMA
February 27, 2019
0
150

 Back-Translation_Sampling_by_Targeting_Difficult_Words_in_Neural_Machine_Translation.pdf

Avatar for MARUYAMA

MARUYAMA

February 27, 2019
Tweet

More Decks by MARUYAMA

See All by MARUYAMA
vampire.pdf
Avatar for MARUYAMA tmaru0204
0
170
Misspelling_Oblivious_Word_Embedding.pdf
Avatar for MARUYAMA tmaru0204
0
180
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
Avatar for MARUYAMA tmaru0204
0
170
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
160
20191028_literature-review.pdf
Avatar for MARUYAMA tmaru0204
0
140
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
130
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
Avatar for MARUYAMA tmaru0204
0
160
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
Avatar for MARUYAMA tmaru0204
0
150
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
150

Featured

See All Featured
Learning to Love Humans: Emotional Interface Design
Avatar for Aarron Walter aarron
273
40k
How to Ace a Technical Interview
Avatar for Jacob Kaplan-Moss jacobian
277
23k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
Avatar for Rebecca Miller-Webster rmw
34
3k
Faster Mobile Websites
Avatar for Dean Hume deanohume
307
31k
Performance Is Good for Brains [We Love Speed 2024]
Avatar for Tammy Everts tammyeverts
10
930
A designer walks into a library…
Avatar for Paul Jervis Heath pauljervisheath
207
24k
The Art of Programming - Codeland 2020
Avatar for Erika Heidi erikaheidi
54
13k
Music & Morning Musume
Avatar for Bryan Veloso bryan
46
6.6k
Save Time (by Creating Custom Rails Generators)
Avatar for Garrett Dimon garrettdimon
PRO
31
1.2k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
Avatar for Addy Osmani addyosmani
7
700
Rebuilding a faster, lazier Slack
Avatar for samanthasiow samanthasiow
82
9.1k
Speed Design
Avatar for Sergey Chernyshev sergeychernyshev
32
1k

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