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

Dynamic_Data_Selection_for_Neural_Machine_Trans...

Avatar for MARUYAMA MARUYAMA
March 28, 2019
0
130

 Dynamic_Data_Selection_for_Neural_Machine_Translation.pdf

Avatar for MARUYAMA

MARUYAMA

March 28, 2019
Tweet

More Decks by MARUYAMA

See All by MARUYAMA
vampire.pdf
Avatar for MARUYAMA tmaru0204
0
180
Misspelling_Oblivious_Word_Embedding.pdf
Avatar for MARUYAMA tmaru0204
0
190
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
Avatar for MARUYAMA tmaru0204
0
180
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
170
20191028_literature-review.pdf
Avatar for MARUYAMA tmaru0204
0
160
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
Avatar for MARUYAMA tmaru0204
0
140
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
Avatar for MARUYAMA tmaru0204
0
170
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
160

Featured

See All Featured
The MySQL Ecosystem @ GitHub 2015
Avatar for Sam Lambert samlambert
251
13k
Improving Core Web Vitals using Speculation Rules API
Avatar for Sergey Chernyshev sergeychernyshev
21
1.2k
Music & Morning Musume
Avatar for Bryan Veloso bryan
46
6.9k
Practical Orchestrator
Avatar for Shlomi Noach shlominoach
190
11k
Visualization
Avatar for Eitan Lees eitanlees
149
16k
Fireside Chat
Avatar for paigeccino paigeccino
41
3.7k
Gamification - CAS2011
Avatar for David Bonilla davidbonilla
81
5.5k
Why Our Code Smells
Avatar for Brandon Keepers bkeepers
PRO
340
57k
Optimising Largest Contentful Paint
Avatar for Harry Roberts csswizardry
37
3.5k
Embracing the Ebb and Flow
Avatar for Simon Collison colly
88
4.9k
The Pragmatic Product Professional
Avatar for Laura Van Doore lauravandoore
36
7k
The Art of Programming - Codeland 2020
Avatar for Erika Heidi erikaheidi
56
14k

Transcript

  1. %ZOBNJD%BUB4FMFDUJPO GPS/FVSBM.BDIJOF5SBOTMBUJPO .BSMJFTWBOEFS8FFT "SJBOOB#JTB[[B $ISJTUPG.PO[&/.-1 QBHFTr -JUFSBUVSFSFWJFX /BHBPLB6OJWFSTJUZPG5FDIOPMPHZ5BLVNJ.BSVZBNB

  2. "CTUSBDU ⾣ֶश࣌ؒΛ࡟ݮͭͭ͠ɺੑೳΛվળ ⾣/.5ͷֶशதʹɺಈతʹֶशσʔλΛมԽͤ͞Δख๏ΛఏҊ ⾣طଘͷσʔλબ୒ख๏Λ/.5ʹదԠ͠ɺޮՌΛݕূ ˠ1#.5ʹ͸ޮՌత͕ͩɺ/.5ʹ͓͍ͯ͸͋·ΓޮՌ͕ͳ͍

  3. *OUSPEVDUJPO ⾣ͭͷ࣮ݧ ɾطଘͷσʔλબ୒ख๏ 4UBUJD%BUB4FMFDUJPO ɾ/.5ʹ߹Θͤͨσʔλબ୒ख๏ %ZOBNJD%BUB4FMFDUJPO 4BNQMJOH (SBEVBMpOFUVOJOH

  4. 4UBUJD%BUB4FMFDUJPO ɾ(FOFSBM ɾ*OEPNBJO ςετσʔλͱಉ͡υϝΠϯͷσʔλ ⾣छྨͷݴޠϞσϧΛߏங *OEPNBJO (FOFSBM 4PVSDFTJEF 5BSHFUTJEF º

    ⾣ͭͷίʔύεΛར༻

  5. 4UBUJD%BUB4FMFDUJPO $ίʔύε I*OEPNBJO G(FOFSBM  Cݴޠ fTPVSDFTJEF eUBSHFUTJEF  ⾣֤ݴޠϞσϧΛ༻͍ͯɺDSPTTFOUSPQZEJ⒎FSFODF

    $&% Λܭࢉ શֶशσʔλΛ$&%ॱʹιʔτͯ͠ɺ্ҐOจରΛֶशʹར༻

  6. %ZOBNJD%BUB4FMFDUJPO ⾣4BNQMJOH $&%ʹج͍ͮͨॏΈ෇͖αϯϓϦϯά ςετσʔλͱؔ࿈ͷ͋Δσʔλ͸બ͹Ε΍͍͢

  7. %ZOBNJD%BUB4FMFDUJPO ⾣(SBEVBMpOFUVOJOH FQPDI਺ΛॏͶΔ౓ʹɺؔ࿈ͷ௿͍σʔλΛֶशσʔλ͔Βআ֎

  8. %ZOBNJD%BUB4FMFDUJPO ⾣(SBEVBMpOFUVOJOH iFQPDI໨ͷσʔλαΠζn(i) ЋSFMBUJWFTUBSUTJ[F 㱡Ћ㱡 cGcUSBJOJOHEBUBTJ[F ЌSFUFOUJPOSBUF 㱡Ќ㱡 Б/VNCFSPGDPOTFDVUJWFFQPDI TFMFDUFETVCTFUJTVTFE

    Б㱢

  9. &YQFSJNFOUTFUUJOH ⾣(FSNBOˠ&OHMJTI ⾣.BDIJOF5SBOTMBUJPO4ZTUFNT ɾ/.5&ODPEFSEFDPEFSNPEFMXJUIHMPCBMBUUFOUJPO ɾ1#.5.PTFT

  10. &YQFSJNFOUTFUUJOH ⾣%BUBTFU ɾ&.&"NFEJDBMHVJEFMJOFT ɾ.PWJFEJBMPHVFT ɾ5&%UBMLT ɾ8.5OFXT ֶश։ൃσʔλʹ͸.JY  ධՁʹ͸֤ධՁηοτΛར༻

  11. 3FTVMU ⾣4UBUJDEBUBTFMFDUJPOGPS1#.5BOE/.5 JOEPNBJOͷσʔλͷΈ ˒  4UBUJDEBUBTFMFDUJPO ˔  JOEPNBJOͷσʔλͷΈ ˒

     4UBUJDEBUBTFMFDUJPO ˔  1#.5 /.5

  12. 3FTVMU ⾣%ZOBNJDEBUBTFMFDUJPOGPS/.5 ಉֶ͡श࣌ؒʹ͓͍ͯɺ TUBUJDTFMFDUJPOΑΓྑ͍݁Ռ 8.5OFXTΛআ͘σʔλͰ͸ɺ TUBUJDTFMFDUJPOͷ࠷ऴ݁ՌΑΓ ߴ͍είΞ

  13. 3FTVMU ⾣%ZOBNJDEBUBTFMFDUJPOGPS/.5

  14. $PODMVTJPO ⾣ֶश࣌ؒΛ࡟ݮͭͭ͠ɺੑೳΛվળ ⾣/.5ͷֶशதʹɺಈతʹֶशσʔλΛมԽͤ͞Δख๏ΛఏҊ ⾣طଘͷσʔλબ୒ख๏Λ/.5ʹదԠ͠ɺޮՌΛݕূ ˠ1#.5ʹ͸ޮՌత͕ͩɺ/.5ʹ͓͍ͯ͸͋·ΓޮՌ͕ͳ͍