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
Simple_Unsupervised_Summarization_by_Contextual...
Search
MARUYAMA
December 08, 2019
0
160
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
MARUYAMA
December 08, 2019
Tweet
Share
More Decks by MARUYAMA
See All by MARUYAMA
vampire.pdf
tmaru0204
0
160
Misspelling_Oblivious_Word_Embedding.pdf
tmaru0204
0
170
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
tmaru0204
0
150
20191028_literature-review.pdf
tmaru0204
0
140
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
140
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
tmaru0204
0
140
Simple_Unsupervised_Keyphrase_Extraction_using_Sentence_Embeddings.pdf
tmaru0204
0
180
Featured
See All Featured
It's Worth the Effort
3n
184
28k
Being A Developer After 40
akosma
91
590k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
227
22k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
47
2.7k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
30
2k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
45
9.5k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.2k
How GitHub (no longer) Works
holman
314
140k
Building Applications with DynamoDB
mza
94
6.4k
Optimising Largest Contentful Paint
csswizardry
37
3.2k
The Language of Interfaces
destraynor
157
25k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
41
2.3k
Transcript
4JNQMF6OTVQFSWJTFE4VNNBSJ[BUJPO CZ$POUFYUVBM.BUDIJOH จݙհ
1BQFS ɾ"$- ɾIUUQTXXXBDMXFCPSHBOUIPMPHZ1 ɾQBHFTr
"CTUSBDU ⾣ͭͷݴޠϞσϧͷΈͷγϯϓϧͳڭࢣͳ͠ੜܕཁ ⾣ੜܕཁɾநग़ܕཁͷํͰ༗༻ੑΛࣔͨ͠ ɾ$POUFYUVBMNBUDIJOHNPEFM ɾ%PNBJOqVFODZNPEFM
*OUSPEVDUJPO ⾣ڭࢣͳ͠ཁ ⾣ෳࡶͳϞσϧɾֶशΛඞཁͱ͠ͳ͍ϞσϧΛఏҊ MFOHUIDPOUSPMMFEWBSJBUJPOBMBVUPFODPEFS HFOFSBUJWFBEWFSTBSJBMOFUXPSL ʜ FH
.PEFM ⾣ཁจɺ࣍ͷͭͷಛੑΛຬ͍ͨͯ͠Δඞཁ͕͋Δ ਖ਼֬ੑ 'BJUIGVMOFTT ݪจͷҙຯͱಉ༷ͷҙຯΛ࣋ͭ ྲྀெੑ 'MVFODZ จ๏తʹਖ਼͘͠ཧղͰ͖Δ P(y|x) ∝
pcm (y|x)pfm (y|x)λ ೖྗจॻ x ཁจ y ਖ਼֬ੑ pcm (y|x) ྲྀெੑ pfm (y|x)
$POUFYUVBM.BUDIJOH.PEFM ⾣ਖ਼֬ੑೖྗςΩετͱग़ྗ୯ޠͷίαΠϯྨࣅ pcm (y|x) = N ∏ n=1 qcm (yn
|y<n , x) ͱͨ͠ͱ͖ sω = maxj≥1 Sim(x1:j , ω) ͜͜Ͱ ग़ྗީิޠͱೖྗςΩετͱͷྨࣅΛ ω x1:j qcm (y1 = ω|x) = softmax(s)
$POUFYUVBM.BUDIJOH.PEFM ⾣ॲཧखॱ sω = maxj≥zn−1 Sim(x1:j , ω) ࣍ࣜΑΓ ྨࣅΛܭࢉ
zn−1 ʹରԠ͘ҐஔҎ͔߱͠ߟྀ͠ͳ͍ zn−1 yn−1 ୯ௐੑͷԾఆ ग़ྗ ୯ޠҐஔΛܭࢉ qcm zn ͕ೖྗจॻඌͱͳΔ·Ͱ܁Γฦ͠ zn
%PNBJO'MVFODZ.PEFM ⾣ྲྀெੑݴޠϞσϧ֬ ೖྗจॻʹదͨ͠ޠΛબ͢ΔΑ͏ग़ྗޠኮΛ੍ ݴޠϞσϧͷग़ྗޠኮ7ΛϘϩϊΠׂʹΑΓ੍͖ޠኮ$ʹϚοϐϯά ͋Δڑ্ۭؒͷҙͷҐஔʹஔ͞Εͨෳݸͷʢʣʹରͯ͠ɺ ಉҰڑ্ۭؒͷଞͷ͕Ͳͷʹ͍͔ۙʹΑͬͯྖҬ͚͞Εͨਤͷ͜ͱɻ IUUQTKBXJLJQFEJBPSHXJLJϘϩϊΠਤ 8JLJQFEJBϘϩϊΠਤ
%PNBJO'MVFODZ.PEFM ⾣ྲྀெੑݴޠϞσϧ֬ pfm (y|x) = N ∏ n=1 ∑ ω′∈N(yn
) lm(ω′|y<n ) ϘϊϩΠׂͷʹ ೖྗจॻ୯ޠΛ༻͍Δ ͷϘϩϊΠྖҬΛͱͨ͠ͱ͖ ݴޠϞσϧ֬ yn N(yn )
.PEFM ⾣ཁจɺ࣍ͷͭͷಛੑΛຬ͍ͨͯ͠Δඞཁ͕͋Δ ਖ਼֬ੑ 'BJUIGVMOFTT ݪจͷҙຯͱಉ༷ͷҙຯΛ࣋ͭ ྲྀெੑ 'MVFODZ จ๏తʹਖ਼͘͠ཧղͰ͖Δ P(y|x) ∝
pcm (y|x)pfm (y|x)λ ೖྗจॻ x ཁจ y ਖ਼֬ੑ pcm (y|x) ྲྀெੑ pfm (y|x)
&YQFSJNFOUBMTFUVQ ⾣.PEFM ⾣%BUBTFU ɾੜܕཁ&OHMJTI(JHBXPSEEBUB 3VTI ɾநग़ܕཁ(PPHMFEBUBTFU 'JMJQQPWB
ɾGPSXBSEMBOHVBHFNPEFMPG&-.P ɾMBZFST-45.NPEFM pcm (y|x) pfm (y|x)
2VBOUJUBUJWF3FTVMUT 5BCMFੜܕཁͷ݁Ռ 5BCMFநग़ܕཁͷ݁Ռ
"OBMZTJT ⾣ೖྗจॻͷ୯ޠநग़͚ͩͰͳ͘ ੜͰ͖͍ͯΔ
4VNNBSZ ⾣ͭͷݴޠϞσϧͷΈͷγϯϓϧͳڭࢣͳ͠ੜܕཁ ⾣ੜܕཁɾநग़ܕཁͷํͰ༗༻ੑΛࣔͨ͠ ɾ$POUFYUVBMNBUDIJOHNPEFM ɾ%PNBJOqVFODZNPEFM
None