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

Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=47 MARUYAMA
November 19, 2019
0
61

 Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=128

MARUYAMA

November 19, 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
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
Simple_Unsupervised_Keyphrase_Extraction_using_Sentence_Embeddings.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
85

Featured

See All Featured
A Philosophy of Restraint
C9b18d9dff88a9dd2393364c2b3b21bd?s=48 colly
192
14k
10 Git Anti Patterns You Should be Aware of
Dafc4723e9a1c067796c0fec6f509774?s=48 lemiorhan
638
52k
Happy Clients
C51b39fa3c79ccb99dcb8a076bc98287?s=48 brianwarren
89
5.6k
Building Applications with DynamoDB
39488f9d172ab92fd352f2cd7b73258d?s=48 mza
83
4.6k
JavaScript: Past, Present, and Future - NDC Porto 2020
3ab1249be442027903e1180025340b3f?s=48 reverentgeek
37
3.2k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
F383c6a4dc55e331bbe2987b622cee6b?s=48 stephaniewalter
268
11k
Intergalactic Javascript Robots from Outer Space
6804f1775cb4babfcc3851298566fbce?s=48 tanoku
261
25k
Agile that works and the tools we love
462dad0dd24c568a32dcdb0ae895ae1b?s=48 rasmusluckow
319
19k
Making Projects Easy
C4de88ea47538e4594750e3861a341c8?s=48 brettharned
98
4.3k
Bash Introduction
812e1705ff0f8bc1bcf18587bde687d5?s=48 62gerente
596
210k
Unsuck your backbone
B83d5b590577969ee79a5ad845411a7d?s=48 ammeep
659
55k
Helping Users Find Their Own Way: Creating Modern Search Experiences
3d4519fd34b76fb265fc0237f3792bd4?s=48 danielanewman
7
1k

Transcript

  1. $POUSPMMJOH5FYU$PNQMFYJUZ JO/FVSBM.BDIJOF5SBOTMBUJPO จݙ঺հ

  2. 1BQFS ɾ&./-1*+$/-1 ɾIUUQTXXXBDMXFCPSHBOUIPMPHZ%

  3. "CTUSBDU ⾣ग़ྗ೉қ౓ͷ੍ޚ͕Մೳͳػց຋༁ϞσϧΛఏҊ ⾣ػց຋༁ͱςΩετฏқԽͷNVMUJUBTLMFBSOJOH ⾣NVMUJUBTLMFBSOJOHʹΑΓ QJQFMJOFBQQSPBDIΛ ্ճΔੑೳΛୡ੒

  4. *OUSPEVDUJPO ⾣຋༁จͷ೉қ౓Λ੍ޚ͢Δ͜ͱʹΑΓ ෯޿͍Ϣʔβʹ ⾣ػց຋༁ͱςΩετฏқԽ͸ಠཱʹݚڀ͞Ε͍ͯΔ ⾣ػց຋༁ͱςΩετฏқԽͷNVMUJUBTLMFBSOJOHʹΑΓ  ৘ใΛఏڙͰ͖Δ ຋༁จͷ೉қ౓੍ޚΛࢼΈΔ

  5. .FUIPE5BTL

  6. .FUIPE.PEFM ⾣-45.CBTFEFODPEFSEFDPEFSXJUIBUUFOUJPO ɾIJEEFOTUBUFTPGTJ[F ɾESPQPVU ɾ-45.MBZFST

  7. .FUIPE5SBJOJOHPCKFDUJWF ⾣.VMUJUBTLMFBSOJOH ɾ$PNQMFYJUZDPOUSPMMFE.5TBNQMFT ɾ.5TBNQMFT ɾ5FYUTJNQMJpDBUJPOTBNQMFT

  8. .FUIPE5SBJOJOHPCKFDUJWF ⾣$PNQMFYJUZDPOUSPMMFE.5TBNQMFT ɾTP຋༁จ ɾTJೖྗจ ɾDP຋༁จͷ೉қ౓ ೖྗจ಄ʹϥϕϧͱͯ͠ૠೖ

  9. .FUIPE5SBJOJOHPCKFDUJWF ⾣.5TBNQMFT ɾTP຋༁จ ɾTJೖྗจ

  10. .FUIPE5SBJOJOHPCKFDUJWF ⾣5FYUTJNQMJpDBUJPOTBNQMFT ɾTP຋༁จ ɾT`P೉қ౓DT`P ͷ຋༁จ ɾDT`P ຋༁จͷ೉қ౓ ೖྗจ಄ʹϥϕϧͱͯ͠ૠೖ

  11. .FUIPE5SBJOJOHPCKFDUJWF ⾣.VMUJUBTLMFBSOJOH ɾ$PNQMFYJUZDPOUSPMMFE.5TBNQMFT ɾ.5TBNQMFT ɾ5FYUTJNQMJpDBUJPOTBNQMFT

  12. %BUBTFU$SPTTMJOHVBMBMJHONFOU ⾣/FXTFMBEBUBTFU ɾݪςΩετʹରͯ͠ dͭͷҟͳΔ೉қ౓ͷςΩετ ɾӳޠ هࣄ εϖΠϯޠ هࣄ ⾣."44"MJHO ɾNPOPMJOHVBMUFYUTJNQMJpDBUJPOBMJHOFS

    ɾεϖΠϯޠهࣄΛ(PPHMFUSBOTMBUFͰӳޠʹ຋༁

  13. %BUBTFU$SPTTMJOHVBMBMJHONFOU

  14. &YQFSJNFOUBMTFUUJOH ⾣&WBMVBUJPONFUSJDT ɾ1$$ग़ྗจͱࢀরจ"3*ͷϐΞιϯ૬ؔ ɾ#-&6 ɾ4"3*

  15. 3FTVMUT

  16. 3FTVMUT ⾣Ͳͷఔ౓ ೉қ౓Λ੍ޚͰ͖͍ͯΔͷ͔

  17. 3FTVMUT ⾣"CMBUJPO&YQFSJNFOUT 

  18. $PODMVTJPO ⾣ग़ྗ೉қ౓ͷ੍ޚ͕Մೳͳػց຋༁ϞσϧΛఏҊ ⾣ػց຋༁ͱςΩετฏқԽͷNVMUJUBTLMFBSOJOH ⾣NVMUJUBTLMFBSOJOHʹΑΓ QJQFMJOFBQQSPBDIΛ ্ճΔੑೳΛୡ੒