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
Spacyでお手軽NLP / NLP with spacy
Search
Sponsored
·
Ship Features Fearlessly
Turn features on and off without deploys. Used by thousands of Ruby developers.
→
himkt
June 13, 2018
Programming
1.1k
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Spacyでお手軽NLP / NLP with spacy
2018/06/13のレトリバセミナーのスライドです
himkt
June 13, 2018
More Decks by himkt
See All by himkt
Linformer: paper reading
himkt
0
660
RoBERTa: paper reading
himkt
1
430
NLP SoTA 勉強会 / ner_2019
himkt
2
1.5k
自然言語処理 @ クックパッド / nlp at cookpad
himkt
1
590
Interpretable Machine Learning 6.3 - Prototypes and Criticisms
himkt
2
220
ニューラル固有表現抽出 / Neural Named Entity Recognition
himkt
3
860
ニューラル固有表現抽出器を実装してみる / PyNER
himkt
6
2.2k
Deep Learning Book 10その2 / deep learning book 10 vol2
himkt
2
220
ふわふわ系列ラベリング / ner 2018
himkt
5
880
Other Decks in Programming
See All in Programming
Go 1.27 における memory allocation の高速化
andpad
0
180
「寝てても仕事が進む」Claude Codeで組む第二の脳
tomoyafujita2016
0
330
S3 を使うアプリケーションをローカル完結で動かすことに全力を注いでみた / Running S3 Apps Offline
contour_gara
0
480
AI時代のPHPer生存戦略 ~「言語、もうなんでもよくない?」に本気で向き合う~
vivion
0
430
琵琶湖の水は止められてもNet--HTTPのリトライは止められない / You might be able to stop the water flow of Lake Biwa but you can't stop Net::HTTP retries
luccafort
PRO
0
710
Claude CodeとAgentCore Gatewayを繋ぐ際の認証認可 / Authentication and authorization when connecting Claude Code with AgentCore Gateway
har1101
2
270
為什麼你並不需要ViewModel / No, you don't need a ViewModel
lovee
1
500
これって Effect でできたのでは? / TSKaigi Mashup Kansai #2
susisu
0
240
PHP初心者セッション2026 〜生成AIでは見えない裏側を知る:今だからLAMPを通して仕組みを学ぶ〜
kashioka
0
920
自動化したのに回らない テスト運用の壁―AI時代の品質責任と生産性
mfunaki
0
170
自動化したのに回らないテスト運用の壁ーAI時代の品質責任と生産性
mfunaki
0
130
言葉の格闘技のススメ~紙とペンと言葉から始める、キャリアの描き方~
progresscicada
2
150
Featured
See All Featured
Docker and Python
trallard
47
4.1k
Building Adaptive Systems
keathley
44
3.2k
Intergalactic Javascript Robots from Outer Space
tanoku
273
27k
GraphQLとの向き合い方2022年版
quramy
50
15k
Chasing Engaging Ingredients in Design
codingconduct
0
270
Jess Joyce - The Pitfalls of Following Frameworks
techseoconnect
PRO
1
370
Producing Creativity
orderedlist
PRO
348
40k
How to Grow Your eCommerce with AI & Automation
katarinadahlin
PRO
1
240
The Art of Programming - Codeland 2020
erikaheidi
57
14k
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
63
45k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
35
2.5k
Ecommerce SEO: The Keys for Success Now & Beyond - #SERPConf2024
aleyda
1
2.1k
Transcript
Ͱ͓खܰ/-1 )JSBNBUTV!ϨτϦόηϛφʔ ը૾IUUQTHJUIVCDPNFYQMPTJPOTQB$ZCMPCNBTUFSXFCTJUFBTTFUTJNHMPHPTWH
Tsukuba, M2, NLP himkt
5-%3 w 1ZUIPOͷࣗવݴޠॲཧϥΠϒϥϦͰ͋Δ4QB$Zͷհ w Wͷ͓͠Ζػೳʹ͍ͭͯ w 4QB$ZͰຊޠςΩετΛॲཧ͢Δ
"CPVU4QB$Z ը૾IUUQTTQBDZJP https://spacy.io
IUUQTTQBDZJP "CPVU4QB$Z “Industrial-Strength NLP” w /POEFTUSVDUJWFUPLFOJ[BUJPO w /BNFEFOUJUZSFDPHOJUJPO w 4VQQPSUGPS
MBOHVBHFT w TUBUJTUJDBMNPEFMTGPSMBOHVBHFT w ʜFUD IUUQTHJUIVCDPNFYQMPTJPOTQB$Z
#BTJDVTBHFPG4QB$Z
.BOZ'FBUVSFT ը૾IUUQTTQBDZJPVTBHFGBDUTpHVSFT
'BTUFTUJOUIFXPSME w %FQFOEFODZQBSTFSͷύϑΥʔϚϯεൺֱ w จIUUQTBDMXFCPSHBOUIPMPHZ111QEG w จʹ͋Δͷ41&&%ͷදͰɼ"DDVSBDZࣗલͰ࡞ΒΕͨͷʁ w $IPJͷϕϯνϚʔΫ࣌ʹTQB$ZWະϦϦʔεͳͷͰOB
ը૾IUUQTTQBDZJPVTBHFGBDUTpHVSFT
4QFFEDPNQBSJTPOXJUIPUIFSMJCSBSJFT w ଞͷࣗવݴޠॲཧϥΠϒϥϦͱͷൺֱ w จͰͳ͘࡞ऀ͕ௐࠪͨ͠ͷ DPOEVDUFEJO w ϦϙδτϦIUUQTHJUIVCDPNFYQMPTJPOTQBDZCFODINBSLT
ը૾IUUQTTQBDZJPVTBHFGBDUTpHVSFT
.PEFMDPNQBSJTPO w ݴޠʹΑͬͯෳͷαΠζͷϞσϧ͕͋Δ FO GS FT w 104UBHHFS /&3UBHHFS
%FQFOEFODZQBSTFS w 8JUIPVUBOZQSFQSPDFTTJOH EBUBTFU ը૾IUUQTTQBDZJPVTBHFGBDUTpHVSFT
/-5,BOE4QB$Z w /-5,P⒎FSTTPNFPGUIFTBNFGVODUJPOBMJUZBTTQB$Z w *ODPNQBSJTPOUPTQB$Z /-5,UBLFTBNVDINPSF CSPBEDIVSDIBQQSPBDI w TQB$ZJTBMTPNVDINPSFQFSGPSNBODFGPDVTTFEUIBO/-5, XIFSFUIFUXPMJCSBSJFTQSPWJEFUIFTBNFGVODUJPOBMJUZ
TQB$ZTJNQMFNFOUBUJPOXJMMVTVBMMZCFGBTUFSBOENPSF BDDVSBUF Ҿ༻IUUQTTQBDZJPVTBHFGBDUTpHVSFT
0UIFSMJCSBSJFTBOETQB$Z 1ZUPSDIIUUQTHJUIVCDPNQZUPSDIQZUPSDICMPCNBTUFSEPDTTPVSDF@TUBUJDJNHQZUPSDIMPHPEBSLTWH "MMFO/-1IUUQTHJUIVCDPNBMMFOBJBMMFOOMQCMPCNBTUFSEPDTUBUJDBMMFOOMQMPHPEBSLQOH (FOTJNIUUQTHJUIVCDPN3B3F5FDIOPMPHJFTHFOTJNCMPCEFWFMPQEPDTTSDSFBENF@JNBHFTSBSFQOH $V1ZIUUQTHJUIVCDPNDVQZDVQZCMPCNBTUFSEPDTJNBHFDVQZ@MPHP@QYQOH JOUPSDIUFYU GPS(16BDDFMFSBUJPO XPSEWFDUPS
QJQFMJOF
4QB$ZWͷݸਓతʹ͖ͳػೳ w EJTQMB$ZͰ͌͢Εʔ͠ʔʁ w 4QB$ZͷՄࢹԽϞδϡʔϧ w ͖Ε͍Ͱ͍͍ײ͡ͳը૾Λ࡞ͬͯ͘ΕΔ w ݻ༗දݱநग़ͱΓड͚ղੳͷ݁ՌΛՄࢹԽͯ͘͠ΕΔ w
4QB$ZͰղੳͨ͠ΦϒδΣΫτΛͦͷ··͑Δ w 47(ܗࣜͷը૾͕ग़ྗ͞ΕΔ
8FCαΠτ্ͷ/&3ͷσϞ ը૾IUUQTFYQMPTJPOBJEFNPTEJTQMBDZFOU
4QB$ZY+VQZUFS/PUFCPPL
4QB$ZBOEຊޠ w WͰͷຊޠରԠ 13 w ຊޠܗଶૉղੳث+BOPNFΛϥοϓ͢ΔܗͰ࣮ w WͰͷܗଶૉղੳثҠߦ *TTVF
13 w ຊޠ6OJWFSTBM%FQFOEFODZσʔλ6OJ%JDͰׂ͞Ε͍ͯΔ w +BOPNFݱࡏͷͱ͜Ζ6OJ%JDʹະରԠ w .F$BCʹҠߦ
4QB$ZBOEຊޠ
4QB$ZBOEຊޠ "OTXFSVTF6OJ%JD
4QB$ZBOEຊޠ
ຊޠ/&3%FQFOEFODZQBSTJOHXJUI4QB$Z w ݁ݱࡏͰ͖ͳ͍ w 4QB$ZʹࣗͰ5BHHFS1BSTFSΛֶशͰ͖Δ ػߏ͕Έࠐ·Ε͍ͯΔ w ຊޠ6OJWFSTBM%FQFOEFODJFTެ։͞Ε͍ͯΔ IUUQTHJUIVCDPN6OJWFSTBM%FQFOEFODJFT6%@+BQBOFTF(4%ͳͲ
Ϟσϧࣗ࡞Ͱ͖ΔͷͰʂʁ
"EEJOH-BOHVBHFTVQQPSU 4QB$ZͷݴޠϞδϡʔϧͷ ίϯϙʔωϯτ ը૾IUUQTTQBDZJPVTBHFBEEJOHMBOHVBHFTTFDUJPOUSBJOJOH
"EEJOH-BOHVBHFTVQQPSU ը૾IUUQTTQBDZJPVTBHFBEEJOHMBOHVBHFTTFDUJPOUSBJOJOH 1PXFSFECZ.F$BC 4QB$ZͷֶशϞδϡʔϧ͕͑ͳ͍ʁ
ຊޠTQB$Zͷݱࡏͷʁ w ࣙॻ͕6OJ%JDͰ͋Δ͜ͱ͕ఆ͞Ε͍ͯΔ JTTVF w ʢ͓ͦΒ͘ʣଟ͘ͷڥͰ.F$BCͷσϑΥϧτࣙॻ*1"EJD w <50%0>+BQBOFTF5PLFOJ[FSͰ5BHHFSΛ࡞͍ͬͯΔ͕ɼ ͜ͷίϯετϥΫλͷҾ֎෦͔Β৮Εͳͦ͏
w ൃԻ͕ະొͷ୯ޠΛղੳ͢ΔͱΤϥʔ *1"EJD 13 w ࣙॻ͝ͱͷग़ྗͷࠩҟΛٵऩ͢ΔΠϯλʔϑΣʔε͕ඞཁʁ w /&3%FQFOEFODZ1BSTJOHͷϞσϧ·ͩଘࡏ͠ͳ͍ w ݱࡏA"MQIBUPLFOJ[BUJPOTVQQPSUA w ͔ͪॻ͖͕ඞཁͳݴޠͷରԠͲ͏͢Εʜ w தࠃޠࣅͨঢ়گͰࢭ·͍ͬͯΔ 13
͜ΕΛΕͱΓ͋͑ͣςετͰ͖ͦ͏ USBWJTͰ.F$BCΛΠϯετʔϧ͢ΔΑ͏ʹ͢Δ TQBDZNPEFMTʹ6OJ%JDΛొ͢Δ QZUIPONTQBDZEPXOMPBEKBΛඋ͢Δ /&3ͱ%FQFOEFODZ1BSTJOH͋ͱͰௐΔʜ
·ͱΊ w ࣗવݴޠॲཧϥΠϒϥϦTQB$Zͷհ w *OEVTUSZൃͷࣗવݴޠॲཧϥΠϒϥϦ w WͰೖͬͨՄࢹԽϞδϡʔϧ͕͍͍ײ͡ w EJTQMB$ZΛ͍͍ͬͨײ͡ͳՄࢹԽ w
TQB$ZͰͷຊޠςΩετॲཧ·ͩෆશ w ݱঢ়ܗଶૉղੳͷΠϯλʔϑΣʔε QJQJOTUBMMTQBDZ 3VO5IJTDPNNBOE