Slide 1

Slide 1 text

ջ͔͖͠CaboChaͷϨγϐΛ΋͏Ұ౓ Pr es ented by log5

Slide 2

Slide 2 text

About “log 5 ” ͨͿΜιϑτ΢ΣΞΤϯδχΞ ొஃͱ͔ࠪಡͱ͔࡞ۂ΋͠·͢ ը૾͸X(ID: log 5 )ͷΞΠίϯ

Slide 3

Slide 3 text

͓඼ॻ͖ CaboChaͱ͸ʁ Πϯετʔϧͯ͠ΈΑ͏ ࢖ͬͯΈΑ͏ ׆༻ͯ͠ΈΑ͏

Slide 4

Slide 4 text

CaboChaͱ͸ʁ ೔ຊޠ܎Γड͚ղੳث จষͷ܎Γड͚ߏ଄Λ෼ੳͯ͘͠ΕΔ Ͳͷ୯ޠ͕Ͳͷ୯ޠʹ܎͍ͬͯΔ͔͕Θ͔Δ

Slide 5

Slide 5 text

“ଠ࿠͸Ֆࢠ͕ಡΜͰ͍ΔຊΛ ࣍࿠ʹ౉ͨ͠”

Slide 6

Slide 6 text

No content

Slide 7

Slide 7 text

ͱ͜ΖͰɺΈͳ͞Μ͸ ೔ৗͰ͜ΜͳจষΛॻ͍ͯ͠·ͬͨ͜ͱɺͳ͍Ͱ͔͢ʁ

Slide 8

Slide 8 text

“ࢲ͸ܑͱ෕Λܴ͑ʹۭߓʹ޲͔ͬͨɻ”

Slide 9

Slide 9 text

“ࢲ͸ܑͱ෕Λܴ͑ʹۭߓʹ޲͔ͬͨɻ” ʮࢲ͸ܑͱʯ෕Λܴ͑ʹۭߓʹ޲͔ͬͨʁ ࢲ͸ʮܑͱ෕Λʯܴ͑ʹۭߓʹ޲͔ͬͨʁ

Slide 10

Slide 10 text

No content

Slide 11

Slide 11 text

CaboChaͱ͸ʁ ೔ຊޠ܎Γड͚ղੳث จষͷ܎Γड͚ߏ଄Λ෼ੳͯ͘͠ΕΔ Ͳͷ୯ޠ͕Ͳͷ୯ޠʹ܎͍ͬͯΔ͔͕Θ͔Δ ޡղ͕ੜ·ΕΔ༨஍Λݕग़Ͱ͖Δ…͔΋͠Εͳ͍ Cabochaࣗମʹᐆດੑݕग़ͷػೳ͸ͳ͍͕ɺͦͷ଍͕͔ΓʹͳΔ

Slide 12

Slide 12 text

CaboChaͱ͸ʁ Cabochaࣗମʹᐆດੑݕग़ͷػೳ͸ͳ͍͕ɺͦͷ଍͕͔ΓʹͳΔ ࠷ऴతʹ͜͏͍͏άϥϑΛ࡞ΕΔͱ͍͏఺͕΋͏͍͢͝

Slide 13

Slide 13 text

Πϯετʔϧͯ͠ΈΑ͏ ެࣜαΠτΛಡ΋͏(ಛʹWindows؀ڥͷํ) https: // taku910.github.io/cabocha/ ࣄલʹ CRF ++ ͱ MeCab ΛΠϯετʔϧ͢Δ Chasen Ͱ͸ಈ࡞͠·ͤΜ macOSͳΒ brew install cabocha ͰҰൃ

Slide 14

Slide 14 text

※͔͜͜Βઌ͸macOSΛϕʔεʹઆ໌͕ਐΈ·͕͢ɺ ଞͷOSͰ΋֓Ͷಉ͡Α͏ʹૢ࡞Ͱ͖Δͱࢥ͍·͢

Slide 15

Slide 15 text

࢖ͬͯΈΑ͏ ࢼ͠ʹ࢖͏ͳΒλʔϛφϧ͔Β΋ར༻Մೳ λʔϛφϧͰ cabocha ͱೖྗ͢Δͱىಈ จষೖྗ଴ػঢ়ଶʹͳΔͷͰɺ޷͖ͳจষΛೖྗ͢Δ

Slide 16

Slide 16 text

No content

Slide 17

Slide 17 text

“ࢲ͸ܑͱ෕Λܴ͑ʹۭߓʹ޲͔ͬͨɻ”

Slide 18

Slide 18 text

No content

Slide 19

Slide 19 text

No content

Slide 20

Slide 20 text

No content

Slide 21

Slide 21 text

“෕͕ւ֎ग़ுͰखʹೖΕͨ࣌ܭΛɺ ૆෕͕ݟͨ໨ΛؾʹೖΓɺࢲʹৡͬͯ͘Εͨɻ”

Slide 22

Slide 22 text

No content

Slide 23

Slide 23 text

No content

Slide 24

Slide 24 text

No content

Slide 25

Slide 25 text

“฼͕ҎલۙॴͷΧϑΣͰ஌Γ߹ͬͨళओ͕։࠵͍ͯͨ͠Ξʔτ లͰߪೖͨ͠ֆը͕ɺࢲ͕ඒज़ؗͰݟͨ͜ͱ͕͋ΔըՈͷ࡞඼ ͩͬͨͱޙ͔Β஌Γɺ࡞඼ूΛਤॻؗͰआΓ͖ͯͯ༑ਓʹקΊ Α͏ͱҰ౓ߟ͑ͨ΋ͷͷɺ͢Ͱʹ༑ਓ͕ಉ͡ըՈʹ͍ͭͯݚڀ ͍ͯͨ͜͠ͱΛࠓ೔஌ͬͨɻ”

Slide 26

Slide 26 text

No content

Slide 27

Slide 27 text

No content

Slide 28

Slide 28 text

No content

Slide 29

Slide 29 text

࢖ͬͯΈΑ͏ ࢼ͠ʹ࢖͏ͳΒλʔϛφϧ͔Β΋ར༻Մೳ λʔϛφϧͰ cabocha ͱೖྗ͢Δͱىಈ จষೖྗ଴ػঢ়ଶʹͳΔͷͰɺ޷͖ͳจষΛೖྗ͢Δ Ҿ਺ͱͯ͠ -f1 Λࢦఆ͢Δͱɺৄࡉ৘ใ͕ಘΒΕΔ

Slide 30

Slide 30 text

No content

Slide 31

Slide 31 text

No content

Slide 32

Slide 32 text

No content

Slide 33

Slide 33 text

No content

Slide 34

Slide 34 text

No content

Slide 35

Slide 35 text

No content

Slide 36

Slide 36 text

͜ͷग़ྗΛͦͷ··෼ղͯ͠΋͍͍Ͱ͕͢…໘౗ ϓϩάϥϛϯάݴޠͰαοͱ࢖͍͍ͨ Python༻ͷWrapper: cabocha-python Λ࢖ͬͯΈΑ͏ ଞͷݴޠΑΓಋೖɾֶशίετ௿ͦ͏ʢθϩͰ͸ͳ͍ʣ ωοτ্ʹؔ࿈هࣄ΋ଟ͍ҹ৅

Slide 37

Slide 37 text

“cabocha-python” Python Ͱ CaboCha ͕ར༻Ͱ͖Δ ίϚϯυͷग़ྗΛ෼ղ͢ΔͨΊͷॲཧΛࣗ෼Ͱॻ͔ͣʹࡁΉ ܎Γ݁ͼͷؔ܎ΛൺֱతָʹऔΓग़ͤΔ ॳ৺ऀτϥοϓ͋Γ

Slide 38

Slide 38 text

“cabocha-python” ΛΠϯετʔϧ ॳ৺ऀτϥοϓ͋Γ جຊతʹ pip install ͰΠϯετʔϧ͢Δ͜ͱʹͳΔ͕…

Slide 39

Slide 39 text

No content

Slide 40

Slide 40 text

No content

Slide 41

Slide 41 text

“cabocha-python” ΛΠϯετʔϧ ॳ৺ऀτϥοϓ͋Γ جຊతʹ pip install ͰΠϯετʔϧ͢Δ͜ͱʹͳΔ͕… 2024 ೥ݱࡏɺ΍ͨΒ෺ʑ͍͠Τϥʔ͕ग़Δ

Slide 42

Slide 42 text

“cabocha-python” ΛΠϯετʔϧ ॳ৺ऀτϥοϓ͋Γ ֤छPath৘ใΛڭ͑ͯ͋͛Δͱղܾ͢Δ…৔߹͕͋Δ

Slide 43

Slide 43 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ Πϯετʔϧ͕ऴΘΕ͹ɺ͋ͱ͸࢖͏͚ͩʂ ͳΜͰ͕͢…

Slide 44

Slide 44 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ Πϯετʔϧ͕ऴΘΕ͹ɺ͋ͱ͸࢖͏͚ͩʂ macOSͷ৔߹ɺApple Silicon Λ౥ࡌ͍ͯ͠Δͱߋʹ᠘͕

Slide 45

Slide 45 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ Πϯετʔϧ͕ऴΘΕ͹ɺ͋ͱ͸࢖͏͚ͩʂ macOSͷ৔߹ɺApple Silicon Λ౥ࡌ͍ͯ͠Δͱߋʹ᠘͕ ↓ͷίʔυ͕࣮ߦ࣌ΤϥʔʹͳΓ·͢

Slide 46

Slide 46 text

࣮ߦ࣌Τϥʔ (Symbol not found) ੩తղੳͰ͸Τϥʔ͕ग़ͳ͍ͷͰɺૺ۰͢Δͱμϝʔδ͕େ͖͍… ଟ෼ɺΠϯετʔϧ࣌ʹམͱ͖ͯͨ͠ϑΝΠϧ͕ Apple Silicon ͱ஥͕ѱ͍ͷ͕ݪҼ

Slide 47

Slide 47 text

࣮ߦ࣌Τϥʔ (Symbol not found) ੩తղੳͰ͸Τϥʔ͕ग़ͳ͍ͷͰɺૺ۰͢Δͱμϝʔδ͕େ͖͍… ଟ෼ɺΠϯετʔϧ࣌ʹམͱ͖ͯͨ͠ϑΝΠϧ͕ Apple Silicon ͱ஥͕ѱ͍ͷ͕ݪҼ ιʔείʔυ͔ΒϏϧυ͢Ε͹ղܾ͢Δ…৔߹͕͋Γ·͢ ↓ͷΑ͏ͳखॱͰ࠶Πϯετʔϧ

Slide 48

Slide 48 text

࠷ॳʹ cabocha Λ࠶Πϯετʔϧ ͨͩ͠ɺιʔείʔυ͔ΒϏϧυ͢Δ ͦͷͨΊ -s (·ͨ͸ -- build-from-source) Λࢦఆ͢Δ

Slide 49

Slide 49 text

࠷ॳʹ cabocha Λ࠶Πϯετʔϧ ͳͲͱ͍͏ͪΐͬͱා͍͜ͱݴΘΕ·͕͢ɺແࢹɻʢଞʹํ๏ͳ͍΋Μ…ʣ Warning: building from source is not supported! You're on your own. Failures are expected so don't create any issues, please!

Slide 50

Slide 50 text

࠷ॳʹ cabocha Λ࠶Πϯετʔϧ ࣍ʹ cabocha-python Λ࠶Πϯετʔϧ Apple Silicon Mac ʹద߹͢ΔͨΊ ARCHFLAGS='-arch arm64’ ιʔείʔυ͔ΒόΠφϦΛίϯύΠϧ͢ΔͷͰ -- compile Λ͚ͭΔ

Slide 51

Slide 51 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ ৭ʑ͚͋ͬͨͲɺΠϯετʔϧ͕ऴΘΕ͹ɺ͋ͱ͸࢖͏͚ͩʂ import CaboCha

Slide 52

Slide 52 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ ParserΛ࡞Γɺ෼ղ͢Δ import CaboCha cabocha_parser = CaboCha.Parser() # ղੳثΛ࡞Δ results = cabocha_parser.parse("͜͜ʹ޷͖ͳจষ") # ղੳ͢Δ

Slide 53

Slide 53 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ ParserΛ࡞Γɺ෼ղ͢Δ ͨͩ͠ɺ෼ੳ݁Ռ(͜͜Ͱ͸ results)͸গ͠ѻ͍ͮΒ͍ import CaboCha cabocha_parser = CaboCha.Parser() # ղੳثΛ࡞Δ results = cabocha_parser.parse("͜͜ʹ޷͖ͳจষ") # ղੳ͢Δ

Slide 54

Slide 54 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ ParserΛ࡞Γɺ෼ղ͢Δ ͨͩ͠ɺ෼ੳ݁Ռ(͜͜Ͱ͸ results)͸গ͠ѻ͍ͮΒ͍ [ৄ͍͠ਓ޲͚] Swig ObjectͳͷͰIDEͷิ׬͕͖͔ͳ͍ import CaboCha cabocha_parser = CaboCha.Parser() # ղੳثΛ࡞Δ results = cabocha_parser.parse("͜͜ʹ޷͖ͳจষ") # ղੳ͢Δ

Slide 55

Slide 55 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ [ৄ͍͠ਓ޲͚] Swig ObjectͳͷͰIDEͷิ׬͕͖͔ͳ͍ C++ଆͷϔομΛݟʹߦ͔ͳ͍ͱԿ͕࢖͑Δͷ͔Θ͔Βͳ͍

Slide 56

Slide 56 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ ParserΛ࡞Γɺ෼ղ͢Δ ͨͩ͠ɺ෼ੳ݁Ռ(͜͜Ͱ͸ results)͸গ͠ѻ͍ͮΒ͍ ʮ͜ͷΑ͏ʹॻ͘ͷͩʯͱ͍͏આ໌͕ͦ΋ͧ΋Ϝζ͍ import CaboCha cabocha_parser = CaboCha.Parser() # ղੳثΛ࡞Δ results = cabocha_parser.parse("͜͜ʹ޷͖ͳจষ") # ղੳ͢Δ ԿΛॻ͚͹͍͍ʁʁʁʁʁʁʁʁʁʁʁʁ

Slide 57

Slide 57 text

“cabocha-python” Λ࢖ͬͯΈΑ͏ ParserΛ࡞Γɺ෼ղ͢Δ ͨͩ͠ɺ෼ੳ݁Ռ(͜͜Ͱ͸ results)͸গ͠ѻ͍ͮΒ͍ ʮ͜ͷΑ͏ʹॻ͘ͷͩʯͱ͍͏આ໌͕ͦ΋ͧ΋Ϝζ͍ ͜ͷྲྀΕͰ͍͖ͳΓC++Ӡʑͷઆ໌Λԡ͠෇͚Δͷ͸ແཧ͕͋Ζ͏͔ͱ

Slide 58

Slide 58 text

શ෦טΈࡅ͍ͯઆ໌͢Δ࣌ؒ΋ͳ͍ͷͰ…

Slide 59

Slide 59 text

ௐཧࡁΈͷ΋ͷΛ༻ҙ͠·ͨ͠ https: // github.com/log5r/sample-mecabocha

Slide 60

Slide 60 text

ௐཧࡁΈͷ΋ͷΛ༻ҙ͠·ͨ͠ https: // github.com/log5r/sample-mecabocha main.pyΛ࣮ߦͯ͠ɺจষΛ͍ΕΔ͚ͩ άϥϑ͕ ./out/graph/ ʹग़དྷ·͢

Slide 61

Slide 61 text

No content

Slide 62

Slide 62 text

No content

Slide 63

Slide 63 text

ௐཧࡁΈͷ΋ͷΛ༻ҙ͠·ͨ͠ https: // github.com/log5r/sample-mecabocha ΑΖ͚͠Ε͹ࢼͯ͠Έ͍ͯͩ͘͞

Slide 64

Slide 64 text

ௐཧࡁΈͷ΋ͷΛ༻ҙ͠·ͨ͠ https: // github.com/log5r/sample-mecabocha ΑΖ͚͠Ε͹ࢼͯ͠Έ͍ͯͩ͘͞ ϒϨʔΫϙΠϯτషͬͯ؍࡯͢Δ΋Α͠

Slide 65

Slide 65 text

·ͩ·ͩਚ͖ͳ͍CaboChaͷັྗ ຊ೔঺հͰ͖ͳ͔ͬͨ΋ͷ ղੳϨΠϠͷ࿩ ݻ༗දݱղੳ σʔλʹΑΔֶश ͳͲͳͲ

Slide 66

Slide 66 text

·ͩ·ͩਚ͖ͳ͍cabochaͷັྗ ຊ೔঺հͰ͖ͳ͔ͬͨ΋ͷ ղੳϨΠϠͷ࿩ ݻ༗දݱղੳ σʔλʹΑΔֶश ͳͲͳͲ ͥͻެࣜαΠτͰʂ https: // taku910.github.io/cabocha/

Slide 67

Slide 67 text

৯ޙͷײ૝(ؾʹͳΔ఺)

Slide 68

Slide 68 text

CaboChaͷཪଆ Support Vector Machines ʹجͮ͘೔ຊޠ܎Γड͚ղੳث Support Vector Machines ͸ػցֶशΞϧΰϦζϜͷҰͭ ೔ຊޠͷจʹ͓͚Δ୯ޠಉ࢜ͷ܎Γड͚ؔ܎Λ෼ྨɾ༧ଌ

Slide 69

Slide 69 text

CaboChaͷཪଆ ೔ຊޠͷจʹ͓͚Δ୯ޠಉ࢜ͷ܎Γड͚ؔ܎Λ෼ྨɾ༧ଌ ژ౎େֶςΩετίʔύε 4 . 0 ౳Λ༻ֶ͍ͯश

Slide 70

Slide 70 text

CaboChaͷཪଆ ژ౎େֶςΩετίʔύε 4 . 0 ຖ೔৽ฉͷهࣄʹ֤छݴޠ৘ใΛਓखͰ෇༩ 1995 ೥ 1 ݄ 1 ೔͔Β 17 ೔·Ͱͷશهࣄɺ໿ 2 ສจɺ 1 ݄͔Β 12 ݄ ·Ͱͷࣾઆهࣄɺ໿ 2 ສจɺܭ໿ 4 ສจʹରͯ͠ɺܗଶૉɾߏจ ৘ใΛ෇༩

Slide 71

Slide 71 text

CaboChaͷཪଆ ೔ຊޠͷจʹ͓͚Δ୯ޠಉ࢜ͷ܎Γड͚ؔ܎Λ෼ྨɾ༧ଌ ژ౎େֶςΩετίʔύε 4 . 0 ౳Λ༻ֶ͍ͯश ιʔε: “ 1995 ೥ 1 ݄ 1 ೔͔Β 17 ೔·Ͱͷશهࣄ”

Slide 72

Slide 72 text

ؾʹͳΔ͜ͱ ޠኮྗ େৎ෉ʁ

Slide 73

Slide 73 text

ؾʹͳΔ͜ͱ ޠኮྗ ΋ͱ΋ͱݹ͍πʔϧͳͷͰɺ৽ޠͷղੳ͕ෆ҆ఆͳ͜ͱ΋…?

Slide 74

Slide 74 text

“ྩ࿨̒೥ʹ͸ೣϛʔϜ͕όζͬͨ͜ͱ͕͋Δɻ”

Slide 75

Slide 75 text

No content

Slide 76

Slide 76 text

No content

Slide 77

Slide 77 text

No content

Slide 78

Slide 78 text

ؾʹͳΔ͜ͱ ޠኮྗ ͦ΋ͦ΋ݹ͍πʔϧͳͷͰɺ৽ޠͷղੳ͕ෆ҆ఆͳ͜ͱ΋…? ͦ͏͍͑͹ɺCaboCha͸MeCabʹґଘ

Slide 79

Slide 79 text

MeCabͷޠኮྗ ద੾ͳࣙॻΛબͿͱޠኮྗ্͕͕Δ໛༷ JumanDic IPADic NAIST-jdic UniDic Neologd

Slide 80

Slide 80 text

MeCabͷޠኮྗ ద੾ͳࣙॻΛબͿͱޠኮྗ্͕͕Δ໛༷ JumanDic IPADic NAIST-jdic UniDic ←།Ұϝϯςφϯε͞ΕͯΔͬΆ͍ (2023൛͕͋Δ) Neologd

Slide 81

Slide 81 text

ؾʹͳΔ͜ͱ MeCabͷࣙॻΛڧԽ͢Ε͹ɺCaboChaͷ෼ੳਫ਼౓΋্͕Δʁ Θ͔Βͳ͍ CaboChaࣗମ͸܇࿅ࡁΈͷϞσϧʹґଘ͢Δ͸ͣ ͨͱ͑͹ɺMeCabͰ৽͍ࣙ͠ॻΛ࢖༻ͯ͠ɺCaboChaଆͰܴ߹͢Δ Α͏ʹ࠶܇࿅͢ΔͳΒΞϦ…? ৄ͍͠ํͷҙݟΛืूதͰ͢

Slide 82

Slide 82 text

·ͱΊ CaboCha͸ʢ 2024 ೥Ͱ΋ʣ͍͍ͧ Ұ౓Πϯετʔϧ͢Ε͹ා͘ͳ͍ ܎Γड͚ղੳ͸࣮༻తָ͍ͩ͠͠

Slide 83

Slide 83 text

͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠ ຊ೔঺հͰ͖ͳ͔ͬͨ΋ͷ ղੳϨΠϠͷ࿩ ݻ༗දݱղੳ σʔλʹΑΔֶश ͳͲͳͲ ͥͻެࣜαΠτͰʂ https: // taku910.github.io/cabocha/