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
150
0

 Back-Translation_Sampling_by_Targeting_Difficult_Words_in_Neural_Machine_Translation.pdf

Avatar for MARUYAMA

MARUYAMA

February 27, 2019

More Decks by MARUYAMA

See All by MARUYAMA
vampire.pdf
Avatar for MARUYAMA tmaru0204
0
200
Misspelling_Oblivious_Word_Embedding.pdf
Avatar for MARUYAMA tmaru0204
0
210
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
Avatar for MARUYAMA tmaru0204
0
200
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
180
20191028_literature-review.pdf
Avatar for MARUYAMA tmaru0204
0
160
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
150
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
Avatar for MARUYAMA tmaru0204
0
180
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
Avatar for MARUYAMA tmaru0204
0
160
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
180

Featured

See All Featured
<Decoding/> the Language of Devs - We Love SEO 2024
Avatar for Nikki Halliwell nikkihalliwell
1
190
The State of eCommerce SEO: How to Win in Today's Products SERPs - #SEOweek
Avatar for Aleyda Solis aleyda
2
10k
Primal Persuasion: How to Engage the Brain for Learning That Lasts
Avatar for Mike Taylor tmiket
0
320
Organizational Design Perspectives: An Ontology of Organizational Design Elements
Avatar for Dr. Kim W Petersen kimpetersen
PRO
1
680
Save Time (by Creating Custom Rails Generators)
Avatar for Garrett Dimon garrettdimon
PRO
32
2.8k
[RailsConf 2023] Rails as a piece of cake
Avatar for Vladimir Dementyev palkan
59
6.5k
Imperfection Machines: The Place of Print at Facebook
Avatar for Scott Boms scottboms
270
14k
AI Search:
Where Are We & What Can We Do About It?
Avatar for Aleyda Solis aleyda
0
7.3k
Unsuck your backbone
Avatar for Amy Palamountain ammeep
672
58k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
Avatar for Joe Casabona jcasabona
34
2.7k
Practical Tips for Bootstrapping Information Extraction Pipelines
Avatar for Matthew Honnibal honnibal
25
1.9k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
Avatar for Chris Coyier chriscoyier
508
140k

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