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
0
140
vampire.pdf
MARUYAMA
February 25, 2020
Tweet
Share
More Decks by MARUYAMA
See All by MARUYAMA
Misspelling_Oblivious_Word_Embedding.pdf
tmaru0204
0
170
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
tmaru0204
0
150
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
tmaru0204
0
140
20191028_literature-review.pdf
tmaru0204
0
130
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
tmaru0204
0
120
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
tmaru0204
0
140
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
tmaru0204
0
130
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
tmaru0204
0
130
Simple_Unsupervised_Keyphrase_Extraction_using_Sentence_Embeddings.pdf
tmaru0204
0
170
Featured
See All Featured
Agile that works and the tools we love
rasmusluckow
328
21k
The MySQL Ecosystem @ GitHub 2015
samlambert
250
12k
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
3.6k
Embracing the Ebb and Flow
colly
84
4.5k
Optimising Largest Contentful Paint
csswizardry
33
3k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
173
50k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
3
350
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
192
16k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
7
560
Music & Morning Musume
bryan
46
6.3k
Facilitating Awesome Meetings
lara
51
6.2k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
3
170
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