Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Don_t_Give_Me_the_Details_Just_the_Summary__Topic-Aware_Convolutional_Neural_Networks_for_Extreme_Summarization.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=47 MARUYAMA
October 08, 2018
0
65

 Don_t_Give_Me_the_Details_Just_the_Summary__Topic-Aware_Convolutional_Neural_Networks_for_Extreme_Summarization.pdf

A3ea3bc5dde6ae2dd6eae71da9c418b0?s=128

MARUYAMA

October 08, 2018
Tweet

More Decks by MARUYAMA

See All by MARUYAMA
vampire.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
69
Misspelling_Oblivious_Word_Embedding.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
52
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
62
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
61
20191028_literature-review.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
63
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
46
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
61
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
56
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
A3ea3bc5dde6ae2dd6eae71da9c418b0?s=48 tmaru0204
0
48

Featured

See All Featured
How to Ace a Technical Interview
2f5463832ccb768ccb4a1ca3607c27ef?s=48 jacobian
265
21k
Building a Scalable Design System with Sketch
1177e050db6bafe62885362edf6e3537?s=48 lauravandoore
447
30k
Designing on Purpose - Digital PM Summit 2013
7653c7c449918ff6542880a8c284f5e7?s=48 jponch
106
5.6k
A Tale of Four Properties
8081b26e05bb4354f7d65ffc34cbbd67?s=48 chriscoyier
149
20k
Dealing with People You Can't Stand - Big Design 2015
44b54d2ffcb7857004071cc6795dde11?s=48 cassininazir
350
21k
Designing Dashboards & Data Visualisations in Web Apps
Fde6c3a50ca518a909ef35c22c0ee0e4?s=48 destraynor
224
49k
Build your cross-platform service in a week with App Engine
5f83ef806155b403c3393160ce51f955?s=48 jlugia
219
17k
Making the Leap to Tech Lead
32de0bd2ba869609d26fd052a4622778?s=48 cromwellryan
113
6.9k
Automating Front-end Workflow
96270e4c3e5e9806cf7245475c00b275?s=48 addyosmani
1351
200k
VelocityConf: Rendering Performance Case Studies
96270e4c3e5e9806cf7245475c00b275?s=48 addyosmani
316
22k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
3d4519fd34b76fb265fc0237f3792bd4?s=48 danielanewman
212
20k
In The Pink: A Labor of Love
E837d2996f52008ace055a08fbfff992?s=48 frogandcode
130
21k

Transcript

  1. %POU(JWF.FUIF%FUBJMT +VTUUIF4VNNBSZ 5PQJD"XBSF$POWPMVUJPOBM/FVSBM/FUXPSLT GPS&YUSFNF4VNNBSJ[BUJPO 4IBTIJ/BSBZBO 4IBZ#$PIFO .JSFMMB-BQBUB &./-1 -JUFSBUVSFSFWJFX /BHBPLB6OJWFSTJUZPG5FDIOPMPHZ5BLVNJ.BSVZBNB

  2. "CTUSBDU ɾl&YUSFNFTVNNBSJ[BUJPOzͱ͍͏λεΫΛఆٛ  4JOHMFEPDVNFOUTVNNBSJ[BUJPO  ɾେن໛ͳσʔληοτΛߏங ɾ0SBDMFFYUSBDUJWFTZTUFN΍4UBUFPGUIFBSU BCTUSBDUJWFBQQSPBDIΑΓ΋༏ΕͨϞσϧΛఏҊ

  3. *OUSPEVDUJPO ɾݱࡏͷཁ໿σʔλ͸FYUSBDUJWFBQQSPBDIʹݞೖΕ͢Δ܏޲ ɾBCTUSBDUJWFBQQSPBDIͩͱͯ͠΋ɺ͋·Γந৅Խ͞Εͳ͍ ɾΑΓந৅Խ͞Εͨཁ໿จΛؚΉσʔληοτͰཁ໿ lFYUSFNFTVNNBSJ[BUJPOz

  4. *OUSPEVDUJPO

  5. 5IF94VN%BUBTFU ɾ94VNEBUBTFU##$BSUJDMF  TJOHMFTFOUFODFTVNNBSZ ɾ/FXT 1PMJUJDT 4QPSUT 8FBUIFS #VTJOFTT ʜ

  6. 5IF94VN%BUBTFU ɾطଘσʔληοτͱͷҧ͍ -&"%هࣄઌ಄ͷOจ·ͨ͸N୯ޠΛநग़ &9503"$-&HPMETVNNBSZͱͷ306(&͕࠷େͱͳΔจΛநग़ 3 3 3-306(& 306(& 306(&-

  7. .PEFM ɾ%FDPEFS ɾ&ODPEFS :distributional representation :positional representation :topic distributions of

    words :topic distributions of document

  8. &YQFSJNFOU4FUVQ ɾ$PNQBSJTPOTZTUFNT 30/%0.هࣄ͔ΒϥϯμϜʹจநग़ -&"%Ϧʔυจ &9503"$-&HPMETVNNBSZͱͷ306(&͕࠷େͱͳΔจ 4&24&2BUUFOUJPOCBTFETFRVFODFUPTFRVFODFNPEFM 15(&/ $07( QPJOUFSHFOFSBUPSNPEFM XJUIDPWFSBHFNFDIBOJTN

    $0/744WBOJMMBDPOWPMVUJPOBMTFRVFODFUPTFRVFODFNPEFM

  9. 3FTVMUT

  10. 3FTVMUT $//%BJMZ.BJM /FXTSPPNͰ͸4&24&2 15(&/-&"%͕ͩͬͨʜ

  11. 3FTVMUT $0/744͕3//CBTFETZTUFNTΑΓ΋༏Εͨ݁Ռʹ

  12. 3FTVMUT ɾਓखධՁ จ  ͭͷཁ໿จͷ͏ͪͭΛఏࣔ͠ɺͲͪΒ͕ྑ͍ཁ໿͔ ࠷ྑͳཁ໿ͱ͍ΘΕׂͨ߹  *OGPSNBUJWFOFTT qVFODZͷ؍఺Ͱબ୒ ͭͷهࣄʹରͯ͠໰୊Λͭ༻ҙɺཁ໿จͷΈಡΜͰղ౴

     DPSSFDU QBSUJBM PUIFS

  13. 3FTVMUT

  14. $PODMVTJPOT ɾl&YUSFNFTVNNBSJ[BUJPOzͱ͍͏λεΫΛఆٛ ɾେن໛ͳσʔληοτΛߏங ɾ0SBDMFFYUSBDUJWFTZTUFN΍4UBUFPGUIFBSU BCTUSBDUJWFBQQSPBDIΑΓ΋༏ΕͨϞσϧΛఏҊ

  15. None