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
170
Misspelling_Oblivious_Word_Embedding.pdf
tmaru0204
0
180
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
tmaru0204
0
170
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
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
tmaru0204
0
150
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
tmaru0204
0
150
Featured
See All Featured
Build your cross-platform service in a week with App Engine
jlugia
231
18k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
44
2.4k
Building a Scalable Design System with Sketch
lauravandoore
462
33k
A Tale of Four Properties
chriscoyier
160
23k
The World Runs on Bad Software
bkeepers
PRO
69
11k
Principles of Awesome APIs and How to Build Them.
keavy
126
17k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.8k
Large-scale JavaScript Application Architecture
addyosmani
512
110k
Statistics for Hackers
jakevdp
799
220k
How to train your dragon (web standard)
notwaldorf
95
6.1k
GraphQLの誤解/rethinking-graphql
sonatard
71
11k
Docker and Python
trallard
44
3.5k
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)