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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
MARUYAMA
February 25, 2020
200
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
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
New Earth Scene 8
popppiees
3
2.4k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
It's Worth the Effort
3n
188
29k
Mind Mapping
helmedeiros
PRO
1
260
Navigating the Design Leadership Dip - Product Design Week Design Leaders+ Conference 2024
apolaine
1
360
The Spectacular Lies of Maps
axbom
PRO
1
820
Being A Developer After 40
akosma
91
590k
A Modern Web Designer's Workflow
chriscoyier
698
190k
Scaling GitHub
holman
464
140k
Building Applications with DynamoDB
mza
96
7.1k
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
sira's awesome portfolio website redesign presentation
elsirapls
0
290
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