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
NLP2019_report.pdf
Search
MARUYAMA
March 19, 2019
0
130
NLP2019_report.pdf
MARUYAMA
March 19, 2019
Tweet
Share
More Decks by MARUYAMA
See All by MARUYAMA
vampire.pdf
tmaru0204
0
180
Misspelling_Oblivious_Word_Embedding.pdf
tmaru0204
0
190
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
tmaru0204
0
180
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
tmaru0204
0
170
20191028_literature-review.pdf
tmaru0204
0
160
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
tmaru0204
0
140
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
tmaru0204
0
170
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
160
Featured
See All Featured
How GitHub (no longer) Works
holman
315
140k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
37
2.6k
Navigating Team Friction
lara
190
15k
Raft: Consensus for Rubyists
vanstee
140
7.2k
Building Better People: How to give real-time feedback that sticks.
wjessup
370
20k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
36
6.1k
Imperfection Machines: The Place of Print at Facebook
scottboms
269
13k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
2.5k
Practical Orchestrator
shlominoach
190
11k
Done Done
chrislema
186
16k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Testing 201, or: Great Expectations
jmmastey
46
7.7k
Transcript
ݴޠॲཧֶձ ୈճ࣍େձ ࢀՃใࠂ Ԭٕज़Պֶେֶɹؙࢁւ
ใࠂ༰ ⾣ ΫΤϦɾग़ྗΛߟྀՄೳͳจॻཁϞσϧ ⾣ ग़ྗ੍ޚΛߟྀͨ͠ݟग़͠ੜϞσϧͷͨΊͷ େنίʔύε ਓݟ༤ଠ, ాޱ༤࠸, ాल໌ (ே৽ฉ),
٠ాᔨ, ௗӋೋ (ϨτϦό), Ԭ࡚؍ (౦େ), ס݈ଠ (౦େ), Ԟଜֶ (౦େ) ੪౻͍ͭΈ, ాژհ, େ௩३࢙, ాޫำ, ઙٱࢠ, ా४ೋ (NTT)
ΫΤϦɾग़ྗΛߟྀՄೳͳจॻཁϞσϧ ⾣ ֓ཁ ɾΫΤϦͱग़ྗΛಉ࣌ʹߟྀͰ͖Δ౷ҰతͳϞσϧΛఏҊ ɾ༰બϞσϧ ੜϞσϧ ⾣ ߩݙ ɾ༰બϞσϧʹ͓͚ΔΫΤϦґଘɾඇґଘͷߟྀ ɾ༰બϞσϧʹ͓͚Δग़ྗͷ੍ޚ
ΫΤϦɾग़ྗΛߟྀՄೳͳจॻཁϞσϧ ⾣ ఏҊϞσϧ ɾ༰બϞσϧ ΫΤϦґଘҙػߏʹΑΓɺΫΤϦʹج͍ͮͨॏཁ୯ޠΛબ ΫΤϦඇґଘ୯ޠͷॏཁֶशύϥϝʔλʹؚΊΔ ग़ྗ੍ޚࢀরཁจͷFNCFEEJOHΛೖྗ
ΫΤϦɾग़ྗΛߟྀՄೳͳจॻཁϞσϧ ⾣ ఏҊϞσϧ ɾੜϞσϧ ༰બϞσϧʹΑΔ୯ޠͷॏΈ QPJOUFSHFOFSBUPSNPEFM ग़ྗ੍ޚଘ͞FNCFEEJOHΛೖྗ
ΫΤϦɾग़ྗΛߟྀՄೳͳจॻཁϞσϧ ⾣ ݁Ռ ɾग़ྗΛ͘͢Δͱɺࣝผˢɾ࠶ݱˣ ɾ͍จதʹΑΓॏཁͳใΛ٧ΊࠐΉ͜ͱ͕Ͱ͖͍ͯΔ
ΫΤϦɾग़ྗΛߟྀՄೳͳจॻཁϞσϧ ⾣ ݁Ռ
ग़ྗ੍ޚΛߟྀͨ͠ݟग़͠ੜϞσϧͷͨΊͷେنίʔύε ⾣ ֓ཁ ɾग़ྗ੍ޚϞσϧΛධՁ༻ίʔύεΛߏங ɾຊޠͷݟग़͠ੜͷͨΊͷֶश༻ίʔύεΛߏங +BQBOFTF.VMUJ-FOHUI)FBE-JOF$PSQVT +".6- +BQBOFTF/FXT$PSQVT +/$
ग़ྗ੍ޚΛߟྀͨ͠ݟग़͠ੜϞσϧͷͨΊͷେنίʔύε ⾣ ίʔύε
ग़ྗ੍ޚΛߟྀͨ͠ݟग़͠ੜϞσϧͷͨΊͷେنίʔύε ⾣ ίʔύε ɾ+".6- ࢴ໘ݟग़͠ ͓Αͼ จࣈͷ֤σδλϧݟग़͠ ݄d݄ͷؒʹ৴͞Εͨهࣄ
݅ ɾ+/$ dͷؒʹ৴͞Εͨهࣄ ࢴ໘ݟग़͠ ݅ IUUQXXXBTBIJDPNTIJNCVONFEJBMBC+".6- ແঈ IUUQXXXBTBIJDPNTIJNCVONFEJBMBC+/$ ༗ঈ
ใࠂ༰ ⾣ ΫΤϦɾग़ྗΛߟྀՄೳͳจॻཁϞσϧ ⾣ ग़ྗ੍ޚΛߟྀͨ͠ݟग़͠ੜϞσϧͷͨΊͷ େنίʔύε ਓݟ༤ଠ, ాޱ༤࠸, ాल໌ (ே৽ฉ),
٠ాᔨ, ௗӋೋ (ϨτϦό), Ԭ࡚؍ (౦େ), ס݈ଠ (౦େ), Ԟଜֶ (౦େ) ੪౻͍ͭΈ, ాژհ, େ௩३࢙, ాޫำ, ઙٱࢠ, ా४ೋ (NTT)