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
vampire.pdf
Search
MARUYAMA
February 25, 2020
200
0
Share
vampire.pdf
MARUYAMA
February 25, 2020
More Decks by MARUYAMA
See All by MARUYAMA
Misspelling_Oblivious_Word_Embedding.pdf
tmaru0204
0
210
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
tmaru0204
0
200
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
Simple_Unsupervised_Keyphrase_Extraction_using_Sentence_Embeddings.pdf
tmaru0204
0
200
Featured
See All Featured
Designing for humans not robots
tammielis
254
26k
A brief & incomplete history of UX Design for the World Wide Web: 1989–2019
jct
1
350
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
287
14k
Between Models and Reality
mayunak
3
260
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.6k
A Modern Web Designer's Workflow
chriscoyier
698
190k
Faster Mobile Websites
deanohume
310
31k
Designing Experiences People Love
moore
143
24k
The Straight Up "How To Draw Better" Workshop
denniskardys
239
140k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
128
55k
The B2B funnel & how to create a winning content strategy
katarinadahlin
PRO
1
330
Building Applications with DynamoDB
mza
96
7k
Transcript
Variational Pretraining for Semi-supervised Text Classification จݙհ Suchin Gururangan, Tam
Dang, Dallas Card, Noah A. Smith ACL2019, pages 5880–5894
Abstract ⾣ܰྔͳࣄલֶशख๏ΛఏҊ ɾখنσʔλͰޮతʹֶशՄೳ ɾߴʹಈ࡞ ⾣ςΩετྨλεΫʹ͓͍ͯɺ ɹ&-.P #&35ʹඖఢ͢ΔੑೳΛୡ
Introduction ⾣&-.P #&35ͷࣄલֶशϞσϧ͕ ɹ͘ར༻͞Ε͍ͯΔ ⾣େنͳίʔύεɾܭࢉࢿݯ͕ඞཁ ⾣ܰྔ͔ͭޮՌతͳࣄલֶशํ๏ΛఏҊ
Model ⾣1SFUSBJOJOH ɾ7BSJBUJPOBM"VUP&ODPEFS
Model ⾣1SFUSBJOJOH ɾ7BSJBUJPOBM"VUP&ODPEFS
Model ⾣5FYUDMBTTJpDBUJPO
Model ⾣5FYUDMBTTJpDBUJPO ɾ7".1*3&FNCFEEJOH݁߹ ɾ%FFQ"WFSBHF/FUXPSLͰ Τϯίʔυ
Experimental setup ⾣%BUB ɾࣄલֶशσʔλ ɾྨثֶशςετ d FYBNQMFT JOEPNBJO d
FYBNQMFT
Experimental setup ⾣-PXSFTPVSDFTFUUJOH ɾ#BTFMJOFڭࢣσʔλͷΈͰֶश ɾ4FMGUSBJOJOHڭࢣ͋Γֶश ڭࢣσʔλ Ϟσϧͷ༧ଌ݁Ռ ɾ(-07& *%
JOEPNBJOσʔλͰֶश ɾ(-07& 0% .XPSETͷίʔύεͰֶश
Results ⾣-PXSFTPVSDFTFUUJOH
Results ⾣-PXSFTPVSDFTFUUJOH
Experimental setup ⾣)JHISFTPVSDFTFUUJOH ɾ5SBOTGPSNFSCBTFE&-.P ɾ#&35 GSP[FO pOFUVOJOH QSFUSBJOJOH JOEPNBJO GSP[FO
pOFUVOJOH
Results ⾣)JHISFTPVSDFTFUUJOH
Results ⾣)JHISFTPVSDFTFUUJOH
Results ⾣$PNQVUBUJPOBM3FRVJSFNFOUT
Conclusions ⾣ܰྔͳࣄલֶशख๏ΛఏҊ ɾখنσʔλͰޮతʹֶशՄೳ ɾߴʹಈ࡞ ⾣ςΩετྨλεΫʹ͓͍ͯɺ ɹ&-.P #&35ʹඖఢ͢ΔੑೳΛୡ