Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Extract_and_Edit_An_Alternative_to_Back-Transla...
Search
MARUYAMA
April 15, 2019
120
0
Share
Extract_and_Edit_An_Alternative_to_Back-Translation_for_Unsupervised_Neural_Machine_Translation.pdf
MARUYAMA
April 15, 2019
More Decks by MARUYAMA
See All by MARUYAMA
vampire.pdf
tmaru0204
0
200
Misspelling_Oblivious_Word_Embedding.pdf
tmaru0204
0
210
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
tmaru0204
0
190
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
tmaru0204
0
180
20191028_literature-review.pdf
tmaru0204
0
160
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
tmaru0204
0
150
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
tmaru0204
0
180
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
tmaru0204
0
160
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
tmaru0204
0
180
Featured
See All Featured
Claude Code どこまでも/ Claude Code Everywhere
nwiizo
64
54k
Facilitating Awesome Meetings
lara
57
6.8k
The Impact of AI in SEO - AI Overviews June 2024 Edition
aleyda
5
780
Reality Check: Gamification 10 Years Later
codingconduct
0
2.1k
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
2
610
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
12
1.1k
Collaborative Software Design: How to facilitate domain modelling decisions
baasie
0
180
Context Engineering - Making Every Token Count
addyosmani
9
780
Noah Learner - AI + Me: how we built a GSC Bulk Export data pipeline
techseoconnect
PRO
0
150
Navigating Team Friction
lara
192
16k
Code Reviewing Like a Champion
maltzj
528
40k
Bridging the Design Gap: How Collaborative Modelling removes blockers to flow between stakeholders and teams @FastFlow conf
baasie
0
500
Transcript
&YUSBDUBOE&EJU"O"MUFSOBUJWFUP #BDL5SBOTMBUJPOGPS6OTVQFSWJTFE /FVSBM.BDIJOF5SBOTMBUJPO +JBXFJ8VBOE9JO8BOHBOE8JMMJBN:BOH8BOH/""$- -JUFSBUVSFSFWJFX /BHBPLB6OJWFSTJUZPG5FDIOPMPHZ5BLVNJ.BSVZBNB
"CTUSBDU ⾣ٯ༁ʹΑΓֶशͨ͠Ϟσϧʹൺɺ#-&6ΛQUҎ্վળ ⾣σʔλͷ࣭Λอͪͭͭڭࢣͳֶ͠शΛߦ͏zFYUSBDUFEJUΛఏҊ ⾣ػց༁ͷڭࢣͳֶ͠शख๏ͱͯ͠ɺٯ༁͕͋Δ ˠ͔͠͠ɺٖࣅతʹੜ͞Εͨσʔλͷ࣭͍
*OUSPEVDUJPO TU5SBOTMBUJPOͷ݁ՌΛ UT5SBOTMBUJPOʹೖྗ͠ɺ ݩͷTPVSDFTFOUFODFΛ ෮ݩͰ͖Δ͔ 3FDPOTUSVDUJPO-PTT &YUSBDU&EJUͰಘΒΕͨจͱൺɺ TU5SBOTMBUJPOͷग़ྗ݁Ռ͕ ͲͷఔTPVSDFTFOUFODFͷ ҙຯʹྨࣅ͍ͯ͠Δ͔
$PNQBSBUJWF 5SBOTMBUJPO-PTT
6OTVQFSWJTFE/.5 *OJUJBMJ[BUJPO ⾣Ұൠతʹ࣍ͷTUFQTͰߦΘΕΔ -BOHVBHFNPEFMJOH #BDLUSBOTMBUJPO ˡ&YUSBDUFEJU
6OTVQFSWJTFE/.5 ⾣*OJUJBMJ[BUJPO ݪݴޠଆͱతݴޠଆͷͭͷݴޠۭؒΛରԠ͚ͮΔ ɾ5IFJOGFSSFECJMJOHVBMEJDUJPOBSZ $POOFBVFUBM ɾ4IBSFE#1& -BNQMFFUBM
6OTVQFSWJTFE/.5 ⾣-BOHVBHFNPEFMJOH EFOPJTJOHBVUPFODPEJOHʹΑΓɺݪݴޠଆͱతݴޠଆͷ྆ํͷ ݴޠϞσϧΛֶश ɾθenc , θdec : encoder, decoderͷֶशύϥϝʔλ
ɾVs→s , Vt→t : encoder-decoder language model ɾC(ɾ): noise model (୯ޠͷܽམɾೖΕସ͑)
6OTVQFSWJTFE/.5 ⾣&YUSBDUFEJU
6OTVQFSWJTFE/.5 ⾣&YUSBDUFEJU &YUSBDU &EJU &WBMVBUF
6OTVQFSWJTFE/.5 ⾣&YUSBDUFEJU &YUSBDU ݪݴޠจʹࣅͨҙຯΛ࣋ͭతݴޠจΛऩू &YUSBDU es , et : shared
encoder͔ΒಘΒΕͨ sentence embeddings
6OTVQFSWJTFE/.5 ⾣&YUSBDUFEJU &EJU . FT FU ͷ.BYQPPMJOH &EJU es ,
et : shared encoder͔ΒಘΒΕͨ sentence embeddings
6OTVQFSWJTFE/.5 ⾣&YUSBDUFEJU &WBMVBUF \4JNJMBSJUZ T UcU㱨.`㱮\U ^ ^ͷ͏ͪɺ 4JNJMBSJUZ T
U Λ࠷େԽͤ͞ΔΑ͏ʹֶश &WBMVBUF rs , rt : shared encoder͔ΒಘΒΕͨsentence embeddings t*: Translation systemͷग़ྗ .` U
6OTVQFSWJTFE/.5 ⾣&YUSBDUFEJU ଛࣦؔ ωlm = ωcom = 1
&YQFSJNFOUTFUUJOHT ⾣%BUBTFUT ɾ&OHMJTI'SFODI (FSNBO 3VTTJBO 3PNBOJBO <5SBJO> ɾ8.5NPOPMJOHVBMOFXTDSBXMEBUBTFUT FO GS
EF SV ɾOFXTDSBXMEBUBTFU 8.5`NPOPMJOHVBMEBUBTFUT SP <5FTU> ɾOFXTUFTU FOGS ɾOFXTUFTU FOEF SV SP
3FTVMUT
"CMBUJPO4UVEZ ⾣5IF&⒎FDUPG&YUSBDUJPO/VNCFSL
⾣5IF2VBMJUZPG&YUSBDUJPO.PEFM "CMBUJPO4UVEZ ɾTVQFSWJTFEFYUSBDUJPONPEFM (SFHPJSFBOE-BOHMBJT ͱͷੑೳൺֱ ɾFOGSUSBOTMBUJPOEBUBTFUʹOPJTFΛ༩ ɾͦΕͧΕͷϞσϧ͕நग़ͨ͠UPQLจʹɺ࣮ࡍͷର༁จؚ͕·Ε͍ͯΔ͔Ͳ͏͔
"CMBUJPO4UVEZ ⾣5IF&⒎FDUPG$PNQBSBUJWF5SBOTMBUJPO ɾ$PNQBSBUJWFMPTTͱ.BYJNVNMJLFMJIPPEFTUJNBUJPO .-& MPTTͷൺֱ ɾ.-&MPTTͰɺFYUSBDUFEJUʹΑΓಘΒΕͨతݴޠଆͷจΛͦͷ·· ɹڭࢣσʔλͱͯ͠ར༻
$PODMVTJPO ⾣ٯ༁ʹΑΓֶशͨ͠Ϟσϧʹൺɺ#-&6ΛQUҎ্վળ ⾣ڭࢣͳֶ͠शͷͨΊͷDPNQBSBUJWFUSBOTMBUJPOMPTTΛఏҊ ⾣ٯ༁ͷସͱͳΔɺΑΓޮՌతͳख๏FYUSBDUFEJUΛఏҊ