Spacyでお手軽NLP / NLP with spacy

Ͱ͓खܰ/-1 )JSBNBUTV!ϨτϦόηϛφʔ ը૾IUUQTHJUIVCDPNFYQMPTJPOTQB$ZCMPCNBTUFSXFCTJUFBTTFUTJNHMPHPTWH

Tsukuba, M2, NLP himkt

5-%3 w 1ZUIPOͷࣗવݴޠॲཧϥΠϒϥϦͰ͋Δ4QB$Zͷ঺հ w Wͷ͓΋͠Ζػೳʹ͍ͭͯ w 4QB$ZͰ೔ຊޠςΩετΛॲཧ͢Δ

"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 ࿦จʹ͋Δͷ͸41&&%ͷදͰɼ"DDVSBDZ͸ࣗલͰ࡞ΒΕͨ΋ͷʁ w $IPJͷϕϯνϚʔΫ࣌ʹ͸TQB$ZW͸ະϦϦʔεͳͷͰOB
ը૾IUUQTTQBDZJPVTBHFGBDUTpHVSFT

4QFFEDPNQBSJTPOXJUIPUIFSMJCSBSJFT w ଞͷࣗવݴޠॲཧϥΠϒϥϦͱͷ଎౓ൺֱ w ࿦จͰ͸ͳ͘࡞ऀ͕ௐࠪͨ͠΋ͷ DPOEVDUFEJO w ϦϙδτϦIUUQTHJUIVCDPNFYQMPTJPOTQBDZCFODINBSLT
ը૾IUUQTTQBDZJPVTBHFGBDUTpHVSFT

.PEFMDPNQBSJTPO w ݴޠʹΑͬͯ͸ෳ਺ͷαΠζͷϞσϧ͕͋Δ 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$ZWͷݸਓతʹ޷͖ͳػೳ w EJTQMB$ZͰ͌͢΀Εʔ͠ʔʁ w 4QB$ZͷՄࢹԽϞδϡʔϧ w ͖Ε͍Ͱ͍͍ײ͡ͳը૾Λ࡞ͬͯ͘ΕΔ w ݻ༗දݱநग़ͱ܎Γड͚ղੳͷ݁ՌΛՄࢹԽͯ͘͠ΕΔ w
4QB$ZͰղੳͨ͠ΦϒδΣΫτΛͦͷ··࢖͑Δ w 47(ܗࣜͷը૾͕ग़ྗ͞ΕΔ

8FCαΠτ্ͷ/&3ͷσϞ ը૾IUUQTFYQMPTJPOBJEFNPTEJTQMBDZFOU

4QB$ZY+VQZUFS/PUFCPPL

4QB$ZBOE೔ຊޠ w WͰͷ೔ຊޠରԠ 13 w ೔ຊޠܗଶૉղੳث+BOPNFΛϥοϓ͢ΔܗͰ࣮૷ w WͰͷܗଶૉղੳثҠߦ *TTVF
13 w ೔ຊޠ6OJWFSTBM%FQFOEFODZσʔλ͸6OJ%JDͰ෼ׂ͞Ε͍ͯΔ w +BOPNF͸ݱࡏͷͱ͜Ζ6OJ%JDʹະରԠ w .F$BCʹҠߦ

4QB$ZBOE೔ຊޠ

4QB$ZBOE೔ຊޠ "OTXFSVTF6OJ%JD

4QB$ZBOE೔ຊޠ

೔ຊޠ/&3%FQFOEFODZQBSTJOHXJUI4QB$Z w ݁࿦ݱࡏ͸Ͱ͖ͳ͍ w 4QB$Zʹ͸ࣗ෼Ͱ5BHHFS΍1BSTFSΛֶशͰ͖Δ  ػߏ͕૊Έࠐ·Ε͍ͯΔ w ೔ຊޠ6OJWFSTBM%FQFOEFODJFT͸ެ։͞Ε͍ͯΔ  IUUQTHJUIVCDPN6OJWFSTBM%FQFOEFODJFT6%@+BQBOFTF(4%ͳͲ
Ϟσϧࣗ࡞Ͱ͖ΔͷͰ͸ʂʁ

"EEJOH-BOHVBHFTVQQPSU 4QB$ZͷݴޠϞδϡʔϧͷ  ίϯϙʔωϯτ ը૾IUUQTTQBDZJPVTBHFBEEJOHMBOHVBHFTTFDUJPOUSBJOJOH

"EEJOH-BOHVBHFTVQQPSU ը૾IUUQTTQBDZJPVTBHFBEEJOHMBOHVBHFTTFDUJPOUSBJOJOH 1PXFSFECZ.F$BC  4QB$ZͷֶशϞδϡʔϧ͕࢖͑ͳ͍ʁ

೔ຊޠTQB$Zͷݱࡏͷ໰୊ʁ w ࣙॻ͕6OJ%JDͰ͋Δ͜ͱ͕૝ఆ͞Ε͍ͯΔ JTTVF w ʢ͓ͦΒ͘ʣଟ͘ͷ؀ڥͰ͸.F$BCͷσϑΥϧτࣙॻ͸*1"EJD w <50%0>+BQBOFTF5PLFOJ[FSͰ5BHHFSΛ࡞͍ͬͯΔ͕ɼ  ͜ͷίϯετϥΫλͷҾ਺͸֎෦͔Β৮Εͳͦ͏
w ൃԻ͕ະొ࿥ͷ୯ޠΛղੳ͢ΔͱΤϥʔ *1"EJD 13 w ࣙॻ͝ͱͷग़ྗͷࠩҟΛٵऩ͢ΔΠϯλʔϑΣʔε͕ඞཁʁ w /&3΍%FQFOEFODZ1BSTJOHͷϞσϧ͸·ͩଘࡏ͠ͳ͍ w ݱࡏ͸A"MQIBUPLFOJ[BUJPOTVQQPSUA w ෼͔ͪॻ͖͕ඞཁͳݴޠͷରԠ͸Ͳ͏͢Ε͹ʜ w தࠃޠ΋ࣅͨঢ়گͰࢭ·͍ͬͯΔ 13

͜ΕΛ΍Ε͹ͱΓ͋͑ͣςετ͸Ͱ͖ͦ͏ USBWJTͰ.F$BCΛΠϯετʔϧ͢ΔΑ͏ʹ͢Δ  TQBDZNPEFMTʹ6OJ%JDΛొ࿥͢Δ  QZUIPONTQBDZEPXOMPBEKBΛ੔උ͢Δ /&3ͱ%FQFOEFODZ1BSTJOH͸͋ͱͰௐ΂Δʜ

·ͱΊ w ࣗવݴޠॲཧϥΠϒϥϦTQB$Zͷ঺հ w *OEVTUSZൃͷࣗવݴޠॲཧϥΠϒϥϦ w WͰೖͬͨՄࢹԽϞδϡʔϧ͕͍͍ײ͡ w EJTQMB$ZΛ࢖͍͍ͬͨײ͡ͳՄࢹԽ w
TQB$ZͰͷ೔ຊޠςΩετॲཧ͸·ͩෆ׬શ w ݱঢ়ܗଶૉղੳͷΠϯλʔϑΣʔε QJQJOTUBMMTQBDZ 3VO5IJTDPNNBOE

Spacyでお手軽NLP / NLP with spacy

Spacyでお手軽NLP / NLP with spacy

himkt

More Decks by himkt

Other Decks in Programming

Featured

Transcript

Ͱ͓खܰ/-1 )JSBNBUTV!ϨτϦόηϛφʔ ը૾IUUQTHJUIVCDPNFYQMPTJPOTQB$ZCMPCNBTUFSXFCTJUFBTTFUTJNHMPHPTWH

Tsukuba, M2, NLP himkt

5-%3 w 1ZUIPOͷࣗવݴޠॲཧϥΠϒϥϦͰ͋Δ4QB$Zͷ঺հ w Wͷ͓΋͠Ζػೳʹ͍ͭͯ w 4QB$ZͰ೔ຊޠςΩετΛॲཧ͢Δ

"CPVU4QB$Z ը૾IUUQTTQBDZJP https://spacy.io

IUUQTTQBDZJP "CPVU4QB$Z “Industrial-Strength NLP” w /POEFTUSVDUJWFUPLFOJ[BUJPO w /BNFEFOUJUZSFDPHOJUJPO w 4VQQPSUGPS

#BTJDVTBHFPG4QB$Z

.BOZ'FBUVSFT ը૾IUUQTTQBDZJPVTBHFGBDUTpHVSFT

'BTUFTUJOUIFXPSME w %FQFOEFODZQBSTFSͷύϑΥʔϚϯεൺֱ w ࿦จIUUQTBDMXFCPSHBOUIPMPHZ111QEG w ࿦จʹ͋Δͷ͸41&&%ͷදͰɼ"DDVSBDZ͸ࣗલͰ࡞ΒΕͨ΋ͷʁ w $IPJͷϕϯνϚʔΫ࣌ʹ͸TQB$ZW͸ະϦϦʔεͳͷͰOB

4QFFEDPNQBSJTPOXJUIPUIFSMJCSBSJFT w ଞͷࣗવݴޠॲཧϥΠϒϥϦͱͷ଎౓ൺֱ w ࿦จͰ͸ͳ͘࡞ऀ͕ௐࠪͨ͠΋ͷ DPOEVDUFEJO w ϦϙδτϦIUUQTHJUIVCDPNFYQMPTJPOTQBDZCFODINBSLT

.PEFMDPNQBSJTPO w ݴޠʹΑͬͯ͸ෳ਺ͷαΠζͷϞσϧ͕͋Δ FO GS FT w 104UBHHFS /&3UBHHFS

/-5,BOE4QB$Z w /-5,P⒎FSTTPNFPGUIFTBNFGVODUJPOBMJUZBTTQB$Z w *ODPNQBSJTPOUPTQB$Z /-5,UBLFTBNVDINPSF  CSPBEDIVSDIBQQSPBDI w TQB$ZJTBMTPNVDINPSFQFSGPSNBODFGPDVTTFEUIBO/-5, XIFSFUIFUXPMJCSBSJFTQSPWJEFUIFTBNFGVODUJPOBMJUZ

4QB$ZWͷݸਓతʹ޷͖ͳػೳ w EJTQMB$ZͰ͌͢΀Εʔ͠ʔʁ w 4QB$ZͷՄࢹԽϞδϡʔϧ w ͖Ε͍Ͱ͍͍ײ͡ͳը૾Λ࡞ͬͯ͘ΕΔ w ݻ༗දݱநग़ͱ܎Γड͚ղੳͷ݁ՌΛՄࢹԽͯ͘͠ΕΔ w

8FCαΠτ্ͷ/&3ͷσϞ ը૾IUUQTFYQMPTJPOBJEFNPTEJTQMBDZFOU

4QB$ZY+VQZUFS/PUFCPPL

4QB$ZBOE೔ຊޠ w WͰͷ೔ຊޠରԠ 13 w ೔ຊޠܗଶૉղੳث+BOPNFΛϥοϓ͢ΔܗͰ࣮૷ w WͰͷܗଶૉղੳثҠߦ *TTVF

4QB$ZBOE೔ຊޠ

4QB$ZBOE೔ຊޠ "OTXFSVTF6OJ%JD

4QB$ZBOE೔ຊޠ

೔ຊޠ/&3%FQFOEFODZQBSTJOHXJUI4QB$Z w ݁࿦ݱࡏ͸Ͱ͖ͳ͍ w 4QB$Zʹ͸ࣗ෼Ͱ5BHHFS΍1BSTFSΛֶशͰ͖Δ  ػߏ͕૊Έࠐ·Ε͍ͯΔ w ೔ຊޠ6OJWFSTBM%FQFOEFODJFT͸ެ։͞Ε͍ͯΔ  IUUQTHJUIVCDPN6OJWFSTBM%FQFOEFODJFT6%@+BQBOFTF(4%ͳͲ

"EEJOH-BOHVBHFTVQQPSU 4QB$ZͷݴޠϞδϡʔϧͷ  ίϯϙʔωϯτ ը૾IUUQTTQBDZJPVTBHFBEEJOHMBOHVBHFTTFDUJPOUSBJOJOH

"EEJOH-BOHVBHFTVQQPSU ը૾IUUQTTQBDZJPVTBHFBEEJOHMBOHVBHFTTFDUJPOUSBJOJOH 1PXFSFECZ.F$BC  4QB$ZͷֶशϞδϡʔϧ͕࢖͑ͳ͍ʁ

೔ຊޠTQB$Zͷݱࡏͷ໰୊ʁ w ࣙॻ͕6OJ%JDͰ͋Δ͜ͱ͕૝ఆ͞Ε͍ͯΔ JTTVF w ʢ͓ͦΒ͘ʣଟ͘ͷ؀ڥͰ͸.F$BCͷσϑΥϧτࣙॻ͸*1"EJD w <50%0>+BQBOFTF5PLFOJ[FSͰ5BHHFSΛ࡞͍ͬͯΔ͕ɼ  ͜ͷίϯετϥΫλͷҾ਺͸֎෦͔Β৮Εͳͦ͏

͜ΕΛ΍Ε͹ͱΓ͋͑ͣςετ͸Ͱ͖ͦ͏ USBWJTͰ.F$BCΛΠϯετʔϧ͢ΔΑ͏ʹ͢Δ  TQBDZNPEFMTʹ6OJ%JDΛొ࿥͢Δ  QZUIPONTQBDZEPXOMPBEKBΛ੔උ͢Δ /&3ͱ%FQFOEFODZ1BSTJOH͸͋ͱͰௐ΂Δʜ

·ͱΊ w ࣗવݴޠॲཧϥΠϒϥϦTQB$Zͷ঺հ w *OEVTUSZൃͷࣗવݴޠॲཧϥΠϒϥϦ w WͰೖͬͨՄࢹԽϞδϡʔϧ͕͍͍ײ͡ w EJTQMB$ZΛ࢖͍͍ͬͨײ͡ͳՄࢹԽ w