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
himkt
June 13, 2018
Programming
0
1.1k
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
Tweet
Share
More Decks by himkt
See All by himkt
Linformer: paper reading
himkt
0
590
RoBERTa: paper reading
himkt
1
390
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
560
Interpretable Machine Learning 6.3 - Prototypes and Criticisms
himkt
2
180
ニューラル固有表現抽出 / Neural Named Entity Recognition
himkt
3
770
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
200
ふわふわ系列ラベリング / ner 2018
himkt
5
860
Other Decks in Programming
See All in Programming
The Past, Present, and Future of Enterprise Java
ivargrimstad
0
620
AIで開発はどれくらい加速したのか?AIエージェントによるコード生成を、現場の評価と研究開発の評価の両面からdeep diveしてみる
daisuketakeda
1
220
0→1 フロントエンド開発 Tips🚀 #レバテックMeetup
bengo4com
0
460
Python札幌 LT資料
t3tra
7
1.1k
GISエンジニアから見たLINKSデータ
nokonoko1203
0
190
まだ間に合う!Claude Code元年をふりかえる
nogu66
5
920
リリース時」テストから「デイリー実行」へ!開発マネージャが取り組んだ、レガシー自動テストのモダン化戦略
goataka
0
160
CSC307 Lecture 01
javiergs
PRO
0
650
脳の「省エネモード」をデバッグする ~System 1(直感)と System 2(論理)の切り替え~
panda728
PRO
0
130
AI前提で考えるiOSアプリのモダナイズ設計
yuukiw00w
0
210
Combinatorial Interview Problems with Backtracking Solutions - From Imperative Procedural Programming to Declarative Functional Programming - Part 2
philipschwarz
PRO
0
130
SQL Server 2025 LT
odashinsuke
0
120
Featured
See All Featured
The Curse of the Amulet
leimatthew05
0
6.7k
Evolving SEO for Evolving Search Engines
ryanjones
0
91
ラッコキーワード サービス紹介資料
rakko
0
1.9M
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
Designing for Timeless Needs
cassininazir
0
110
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.3k
How to Think Like a Performance Engineer
csswizardry
28
2.4k
Navigating Weather and Climate Data
rabernat
0
62
The #1 spot is gone: here's how to win anyway
tamaranovitovic
1
880
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
287
14k
Odyssey Design
rkendrick25
PRO
0
450
What’s in a name? Adding method to the madness
productmarketing
PRO
24
3.9k
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