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
Don_t_Give_Me_the_Details_Just_the_Summary__Topic-Aware_Convolutional_Neural_Networks_for_Extreme_Summarization.pdf
Search
MARUYAMA
October 08, 2018
0
120
Don_t_Give_Me_the_Details_Just_the_Summary__Topic-Aware_Convolutional_Neural_Networks_for_Extreme_Summarization.pdf
MARUYAMA
October 08, 2018
Tweet
Share
More Decks by MARUYAMA
See All by MARUYAMA
vampire.pdf
tmaru0204
0
130
Misspelling_Oblivious_Word_Embedding.pdf
tmaru0204
0
130
Simple_Unsupervised_Summarization_by_Contextual_Matching.pdf
tmaru0204
0
130
Controlling_Text_Complexity_in_Neural_Machine_Translation.pdf
tmaru0204
0
120
20191028_literature-review.pdf
tmaru0204
0
120
Hint-Based_Training_for_Non-Autoregressive_Machine_Translation.pdf
tmaru0204
0
100
Soft_Contextual_Data_Augmentation_for_Neural_Machine_Translation_.pdf
tmaru0204
0
120
An_Embarrassingly_Simple_Approach_for_Transfer_Learning_from_Pretrained_Language_Models_.pdf
tmaru0204
0
110
Addressing_Trobulesome_Words_in_Neural_Machine_Translation.pdf
tmaru0204
0
110
Featured
See All Featured
Keith and Marios Guide to Fast Websites
keithpitt
408
22k
How to name files
jennybc
64
93k
What's in a price? How to price your products and services
michaelherold
237
11k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
226
16k
Fontdeck: Realign not Redesign
paulrobertlloyd
76
4.9k
ParisWeb 2013: Learning to Love: Crash Course in Emotional UX Design
dotmariusz
104
6.6k
Docker and Python
trallard
33
2.7k
Building Adaptive Systems
keathley
30
1.9k
How to train your dragon (web standard)
notwaldorf
72
5.2k
Six Lessons from altMBA
skipperchong
20
3k
From Idea to $5000 a Month in 5 Months
shpigford
377
45k
Web development in the modern age
philhawksworth
202
10k
Transcript
%POU(JWF.FUIF%FUBJMT +VTUUIF4VNNBSZ 5PQJD"XBSF$POWPMVUJPOBM/FVSBM/FUXPSLT GPS&YUSFNF4VNNBSJ[BUJPO 4IBTIJ/BSBZBO 4IBZ#$PIFO .JSFMMB-BQBUB &./-1 -JUFSBUVSFSFWJFX /BHBPLB6OJWFSTJUZPG5FDIOPMPHZ5BLVNJ.BSVZBNB
"CTUSBDU ɾl&YUSFNFTVNNBSJ[BUJPOzͱ͍͏λεΫΛఆٛ 4JOHMFEPDVNFOUTVNNBSJ[BUJPO ɾେنͳσʔληοτΛߏங ɾ0SBDMFFYUSBDUJWFTZTUFN4UBUFPGUIFBSU BCTUSBDUJWFBQQSPBDIΑΓ༏ΕͨϞσϧΛఏҊ
*OUSPEVDUJPO ɾݱࡏͷཁσʔλFYUSBDUJWFBQQSPBDIʹݞೖΕ͢Δ ɾBCTUSBDUJWFBQQSPBDIͩͱͯ͠ɺ͋·ΓநԽ͞Εͳ͍ ɾΑΓநԽ͞ΕͨཁจΛؚΉσʔληοτͰཁ lFYUSFNFTVNNBSJ[BUJPOz
*OUSPEVDUJPO
5IF94VN%BUBTFU ɾ94VNEBUBTFU##$BSUJDMF TJOHMFTFOUFODFTVNNBSZ ɾ/FXT 1PMJUJDT 4QPSUT 8FBUIFS #VTJOFTT ʜ
5IF94VN%BUBTFU ɾطଘσʔληοτͱͷҧ͍ -&"%هࣄઌ಄ͷOจ·ͨN୯ޠΛநग़ &9503"$-&HPMETVNNBSZͱͷ306(&͕࠷େͱͳΔจΛநग़ 3 3 3-306(& 306(& 306(&-
.PEFM ɾ%FDPEFS ɾ&ODPEFS :distributional representation :positional representation :topic distributions of
words :topic distributions of document
&YQFSJNFOU4FUVQ ɾ$PNQBSJTPOTZTUFNT 30/%0.هࣄ͔ΒϥϯμϜʹจநग़ -&"%Ϧʔυจ &9503"$-&HPMETVNNBSZͱͷ306(&͕࠷େͱͳΔจ 4&24&2BUUFOUJPOCBTFETFRVFODFUPTFRVFODFNPEFM 15(&/ $07( QPJOUFSHFOFSBUPSNPEFM XJUIDPWFSBHFNFDIBOJTN
$0/744WBOJMMBDPOWPMVUJPOBMTFRVFODFUPTFRVFODFNPEFM
3FTVMUT
3FTVMUT $//%BJMZ.BJM /FXTSPPNͰ4&24&2 15(&/-&"%͕ͩͬͨʜ
3FTVMUT $0/744͕3//CBTFETZTUFNTΑΓ༏Εͨ݁Ռʹ
3FTVMUT ɾਓखධՁ จ ͭͷཁจͷ͏ͪͭΛఏࣔ͠ɺͲͪΒ͕ྑ͍ཁ͔ ࠷ྑͳཁͱ͍ΘΕׂͨ߹ *OGPSNBUJWFOFTT qVFODZͷ؍Ͱબ ͭͷهࣄʹରͯ͠Λͭ༻ҙɺཁจͷΈಡΜͰղ
DPSSFDU QBSUJBM PUIFS
3FTVMUT
$PODMVTJPOT ɾl&YUSFNFTVNNBSJ[BUJPOzͱ͍͏λεΫΛఆٛ ɾେنͳσʔληοτΛߏங ɾ0SBDMFFYUSBDUJWFTZTUFN4UBUFPGUIFBSU BCTUSBDUJWFBQQSPBDIΑΓ༏ΕͨϞσϧΛఏҊ
None