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
MeCabとKerasを使ったテキスト分類
Search
masa-ita
February 23, 2019
Technology
1
440
MeCabとKerasを使ったテキスト分類
masa-ita
February 23, 2019
Tweet
Share
More Decks by masa-ita
See All by masa-ita
Run Instant NeRF on Docker
itagakim
1
2.1k
3D Clustering and Metric Learning
itagakim
0
270
Cloud TPUの使い方〜BigBirdの日本語学習済みモデルを作る〜
itagakim
0
600
多言語学習済みモデルmT5とは?
itagakim
1
570
AWSのGPUを安く使ってTensorFlowモデルを訓練する方法
itagakim
0
300
最近の自然言語処理モデルの動向
itagakim
1
520
ディープラーニングで芸術はできるか?〜生成系ネットワークの進展〜
itagakim
0
270
AWSとTerraform初心者がやってみたこと
itagakim
1
410
IntroductionToTensorFlow2_0.pdf
itagakim
1
310
Other Decks in Technology
See All in Technology
Forget efficiency – Become more productive without the stress
ufried
0
140
Product Engineer Night #6プロダクトエンジニアを育む仕組み・施策
hacomono
PRO
1
470
CyberAgent 生成AI Deep Dive with Amazon Web Services / genai-aws
cyberagentdevelopers
PRO
1
480
Oracle Cloud Infrastructureデータベース・クラウド:各バージョンのサポート期間
oracle4engineer
PRO
27
12k
なんで、私がAWS Heroに!? 〜社外の広い世界に一歩踏み出そう〜
minorun365
PRO
6
1.1k
[AWS JAPAN 生成AIハッカソン] Dialog の紹介
yoshimi0227
0
150
物価高なラスベガスでの過ごし方
zakky
0
380
チームを主語にしてみる / Making "Team" the Subject
ar_tama
4
310
Aurora_BlueGreenDeploymentsやってみた
tsukasa_ishimaru
1
120
事業者間調整の行間を読む 調整の具体事例
sugiim
0
1.5k
オーティファイ会社紹介資料 / Autify Company Deck
autifyhq
9
120k
カメラを用いた店内計測におけるオプトインの仕組みの実現 / ai-optin-camera
cyberagentdevelopers
PRO
1
120
Featured
See All Featured
Docker and Python
trallard
40
3.1k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
107
49k
The Straight Up "How To Draw Better" Workshop
denniskardys
232
140k
RailsConf 2023
tenderlove
29
880
BBQ
matthewcrist
85
9.3k
KATA
mclloyd
29
13k
Designing the Hi-DPI Web
ddemaree
280
34k
jQuery: Nuts, Bolts and Bling
dougneiner
61
7.5k
How GitHub (no longer) Works
holman
311
140k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
126
18k
Building Adaptive Systems
keathley
38
2.2k
The Cult of Friendly URLs
andyhume
78
6k
Transcript
MeCabKeras 2019/2/23 @Python in
3F-*"% Q:<+/M@3F-*8L )9 3F O8L$?.
IDP6S E<6S >16S KFREG6S /M6S C4-*"% 3F-*8L)9 <JNF '0=A#&H ! 5 72; B, ("%
!!$A<7> 7>-=N-Gram .C(2 !$,@ 7>A<A1
0 # $?/<"A<85 3B!$, %&<*'9)+:. %&<*'D46 =;C2E6 0 Ex. MeCab
'!, ",*+$J8 AOIQH=
FORBFO"( E9 RLRB20N16AOIQ H= RLAAG>U &$ CV .@W73 RL?K MS 16E -D16/5:TH= /5:T;=46 )%#+P 46<
livedoor NHN Japan58+- 42 livedoor $' ) #%&* (!*
=. $'1,79 :6;HTML"/<30 https://www.rondhuit.com/download.html#ldcc
livedoor
MeCab
MeCab HN7GSMGegi−69PKPLW`8:%/0-$ &25iGQoegI _@eg1-*,.4'",BC? !.5)(
fdkRm 5'5 V;T[nUJaGoogle Inc. ^p\Ffh]cX +.3-5#><jl = Y ,"5DAbEZ O
MeCab MeCab C++ '& # !*(
Windows %$ https://taku910.github.io/mecab/#download #"+) 32 64 , https://github.com/ikegami-yukino/mecab/releases/tag/v0.996 #"+) Mac %$ Homebrew mecab, mecab-ipadic #!+) Ubuntu %$ apt mecab, mecab-ipadic #!+)
Keras
keras.preprocessing.text.Tokenizer /-.2 /- !%"(8$&5 * #31)76 0)% +4
', fit &5tokenize !%0) %
keras.preprocessing.sequence.pad_sequences ! ( " # $'%
&
BoW: Bag of Words # %EC* G DEC?
- J;/ F<+EC,8=@1/0&%) 58 ()! '"%*$* ,8I209&%) 58 /1 TF-IDF: Term Frequency Inverse Document Frequency EHI2 ><,8 EC:67B4A .1&% )3
Word Embedding a]!.$*2C<@ fTY=!UD :9RPJG5 a]J ?Z10,000 20,000K6
Ni '3&, &.$*2 7<a]![RP7dJ`RPe.$*2 F S< Word Embeddinga]gO Google A; Xb!LWord2vec^V \B W^Ec!80)2H_!LRP IM Word2vec&#(-%1/Qh@Ec!8 )"-1 +4%0)27> Ec!8<@
RNN: Recurrent Neural Network *-H,+.=8 G "!%AB !*DF
@162 ,'/5?)/ G#$&!:(8 RNN> C;79304E LSTMLong Short Term MemoryGRU Gated Recurrent Unit<
BoW DNN
Word EmbeddingGlobalAveragePooling1D
Word EmbeddingRNNLSTM DNN
BoWDNN 0.5E #9("%$)CBoW+/ DNN4: * DBG6GlobalAveragePooling1D1 !$=2F
A LSTM7H2F,- <4: ' ; 7I ?3>8)CLSTM 4: & @:4
NLP,B8?=4-1$!&)%+"C5>@.A 7EFDQ&A-1Sequence-to-Sequence($* Attention :($*.A;3 OpenAIGoogle
Transformer '#Allen Institute 2.ELMo Google G5($*3BERTOpenAI .6GPT-204 <($* 9/