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
An_Embarrassingly_Simple_Approach_for_Transfer_...
Search
MARUYAMA
July 10, 2019
0
150
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
MARUYAMA
July 10, 2019
Tweet
Share
More Decks by MARUYAMA
See All by MARUYAMA
vampire.pdf
tmaru0204
0
180
Misspelling_Oblivious_Word_Embedding.pdf
tmaru0204
0
180
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
tmaru0204
0
180
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
tmaru0204
0
160
20191028_literature-review.pdf
tmaru0204
0
150
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
tmaru0204
0
130
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
tmaru0204
0
160
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
tmaru0204
0
150
Simple_Unsupervised_Keyphrase_Extraction_using_Sentence_Embeddings.pdf
tmaru0204
0
190
Featured
See All Featured
Done Done
chrislema
185
16k
Navigating Team Friction
lara
188
15k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
Producing Creativity
orderedlist
PRO
346
40k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
2.9k
Building a Scalable Design System with Sketch
lauravandoore
462
33k
How to train your dragon (web standard)
notwaldorf
96
6.1k
What's in a price? How to price your products and services
michaelherold
246
12k
Become a Pro
speakerdeck
PRO
29
5.4k
Designing for Performance
lara
610
69k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
331
22k
A better future with KSS
kneath
238
17k
Transcript
"O&NCBSSBTTJOHMZ4JNQMF"QQSPBDIGPS 5SBOTGFS-FBSOJOHGSPN1SFUSBJOFE-BOHVBHF.PEFMT "MFYBOESB$ISPOPQPVMPV $ISJTUPT#B[JPUJT "MFYBOESPT1PUBNJBOPT /""$-)-5 QBHFTr -JUFSBUVSFSFWJFX /BHBPLB6OJWFSTJUZPG5FDIOPMPHZ5BLVNJ.BSVZBNB
"CTUSBDU ⾣FOEUPFOEʹֶशͤ͞ΔγϯϓϧͳసҠֶशख๏ΛఏҊ ⾣ࣄલֶशͨ͠ݴޠϞσϧΛྨλεΫʹpOFUVOJOH ⾣༷ʑͳςΩετྨλεΫͰɺطଘख๏Λ͑ΔੑೳΛୡ
3FMBUFEXPSL ⾣6-.'J5 %JTDSJNJOBUJWFpOFUVOJOH֤ͰֶशΛมԽͤ͞Δ 4MBOUFEUSJBOHVMBSMFBSOJOHSBUFT
.PEFM 4J"5- ⾣-.1SFUSBJOJOH ⾣5SBOTGFSBVYJMJBSZMPTT ɾFYQPOFOUJBMEFDBZPGЍ FQPDIຖʹЍΛࢦతʹݮਰ ɾTFRVFOUJBMVOGSFF[JOH ্ͷ͔Βॱ࣍ղౚ͠ɺpOFUVOJOH
&YQFSJNFOUBMTFUVQT ⾣%BUBTFUT ɾ*SPOZJSPOZEFUFDUJPO ɾ4FOUTFOUJNFOUBOBMZTJT ɾ4$W 4$WTBSDBTNEFUFDUJPO ɾ1TZDI&YQFNPUJPOSFDPHOJUJPO
3FTVMUT ⾣"CMBUJPOTUVEZ
3FTVMUT ⾣/VNCFSPGFYBNQMFT ɾ4J"5- DPOUJOVPVTMJOFT ɾ6-.'J5 EBTIFEMJOFT dσʔλఔͰɺ 6-.'J5ʹඖఢ͢Δੑೳ
3FTVMUT ⾣&YQPOFOUJBMEFDBZPGЍ *OJUJBMWBMVF 'JOBMWBMVF
$PODMVTJPO ⾣FOEUPFOEʹֶशͤ͞ΔγϯϓϧͳసҠֶशख๏ΛఏҊ ⾣ࣄલֶशͨ͠ݴޠϞσϧΛྨλεΫʹpOFUVOJOH ⾣༷ʑͳςΩετྨλεΫͰɺطଘख๏Λ͑ΔੑೳΛୡ