ACL2020 Category Survey: Sentiment Analysis

ACL2020 分野サーベイLT会の資料です。
https://nlpaper-challenge.connpass.com/event/191318/

ACL2020 に採択された sentiment analysis 系論文を読み、傾向をまとめ、気になった論文を詳しく紹介しています。

Transcript

1. ACL2020 Category Survey:
   Sentiment Analysis
   

   View Slide

2. ಺ڮ ݎࢤ
   uchi_k @__uchi_k__
   About me
   yuni, inc. ୅ද
   ʮσʔλυϦϒϯͳ΋ͷͮ͘ΓΛࢧԉ͢ΔʯΛܝ͛ɺ
   UGCղੳ΍ϚʔέςΟϯάσʔλղੳͷडୗɺࣗࣾ
   SleepTechϒϥϯυɺύʔιφϥΠζϚοτϨεͷ
   xSleepΛӡӦ͍ͯ͠·͢ɻ
   former ژେ৘ใӃ, ະ౿2016, ϑϦʔϥϯε,
   FreakOut Machine Learning Engineer
   

   View Slide

3. ACL2020
   ੜ੒ܥɺάϥϑܥͷ࿦จ͕͔ͳΓ૿͑ͨҹ৅
   #&35 3P#&35B౳ͷࣄલֶशݴޠϞσϧʹؔ͢Δݴٴ͕΄΅ඞͣ͋Δ
   ࠶ݱੑͷࢹ఺΍࣮຿΁ͷԠ༻͔Βɺࢦඪͷݟ௚͕͠ਐΜͩ
   ϕετϖʔύʔ΋ɺ/-1λεΫͷςετέʔεΈ͍ͨͳ΋ͷΛఆ
   ٛͯ͠௨ա཰ΛݟΑ͏Έ͍ͨͳ࿩Λ͍ͯͨ͠Γ
   ,OPXMFEHFHSBQIʹճؼͯ͠ɺάϥϑ্Ͱͷԋࢉ΍άϥϑߏ଄ɺֶ
   शΛߦ͏Α͏ͳ࿩͕૿Ճ
   Ҏ্ɺࢲݟͰͨ͠
   

   View Slide

4. Sentiment Analysis
   ͦͷଞ
   
   ൺֱબ޷෼ྨ
   ཁ໿
   
   આಘྗղੳ
   
   ελϯεݕग़
   
   લॲཧ
   
   ΞεϖΫτࣝผ
   
   ײ৘ݪҼϖΞநग़
   
   ΞεϖΫτϕʔεײ৘෼ྨ
   
   ϨϏϡʔίϝϯτ౳ͷ
   VTFSHFOFSBUFE
   DPOUFOUT 6($
   ͷϚΠ
   χϯά͕ଟ͘ɺ࢈ۀԠ༻
   ࢤ޲ͷݚڀ͕ଟ͍෼໺
   6($ͷղੳ͸঎඼ͷΧς
   ΰϦ΍࢖༻ঢ়گ͋Γ͖ͷ
   ײ৘ೝࣝʹͳΔ͜ͱ͕ଟ
   ͍ˠΞεϖΫτϕʔεײ
   ৘෼ྨͷ࿦จ͕ଟ͍
   

   View Slide

5. Sentiment Analysis
   4FOUJNFOUBOBMZTJTͷ໰୊ҙࣝͱͯ͠ଟ͍ͷ͸ɺσʔλ͕গͳ͍ɺ
   ݸผλεΫͷͭͳ͗߹ΘͤͰ૬ޓ࡞༻ΛߟྀͰ͖͍ͯͳ͍ɺ৽͍͠໰୊
   ΁ͷରॲͷͭͷύλʔϯ
   σʔλ͕গͳ͍໰୊ʹରͯ͠͸ɺผݴޠϦιʔεͷར༻ɺผυϝΠ
   ϯͷར༻ɺ֎෦஌ࣝάϥϑͷར༻ɺޮ཰తͳΞϊςʔγϣϯ౳Ͱରॲ
   $SPTT-JOHVBM6OTVQFSWJTFE4FOUJNFOU$MBTTJpDBUJPOXJUI
   .VMUJ7JFX5SBOTGFS-FBSOJOHࢿݯͷগͳ͍ݴޠʹ͍ͭͯɺڭࢣͳ
   ͠ػց຋༁ͱݴޠ൑ผثΛ࢖ͬͨڭࢣͳ͠ݴޠԣஅηϯνϝϯτ෼ྨϞ
   σϧΛఏҊɻ
   

   View Slide

6. $SPTT-JOHVBM6OTVQFSWJTFE4FOUJNFOU$MBTTJpDBUJPO
   XJUI.VMUJ7JFX5SBOTGFS-FBSOJOH
   #σʔλ͕গͳ͍໰୊΁ͷରॲྫɿผݴޠϦιʔεͷར༻
   )POHMJBOH'FJ #BJEV3FTFBSDI
   1JOH-J #BJEV3FTFBSDI
   "$-
   ࢿݯͷগͳ͍ݴޠʹ͍ͭͯɺڭࢣͳ͠ػց຋༁ͱݴޠ൑ผثΛ࢖ͬͨ
   ڭࢣͳ͠ݴޠԣஅηϯνϝϯτ෼ྨϞσϧΛఏҊɻ
   ຋༁ثͱݴޠ൑ผثʹΑΔݴޠ
   BEWFSTBSJBMͳֶशͰݴޠීว
   ͳಛ௃ۭؒΛֶश͢Δ
   λʔήοτݴޠͷϥϕϧ෇͖Ϧ
   ιʔε΋ιʔεݴޠͱͷΫϩε
   ϦϯΨϧιʔε΋ඞཁͱ͠ͳ͍
   ఺͕৽͍͠
   

   View Slide

7. Sentiment analysis
   ݸผλεΫͷͭͳ͗߹Θͤʹͳ͍ͬͯΔɺͱ͍͏ͷ͸ɺྫ͑͹Ξε
   ϖΫτϕʔεηϯνϝϯτ෼ੳͰͷΞεϖΫτ༻ޠநग़ɺҙݟ༻ޠந
   ग़ɺηϯνϝϯτ෼ੳͷஈ֊ʹͳ͍ͬͯΔɺͳͲ
   λεΫͷ਺चͭͳ͗͸λεΫ͝ͱͷ஌ݟ͕ڞ༗͞Εͳ͍ɺ૬ޓ࡞༻Λ͏
   ·ֶ͘शͰ͖ͳ͍ͳͲͷ໰୊఺͕͋ΓɺUSBOTGPSNFSͳͲΛ࢖ͬͨ
   FOEUPFOEͳख๏΍HSBQIBUUFOUJPOͳͲͷσʔλߏ଄Ͱରॲ͢
   ΔͳͲͷख๏͕ݟΒΕͨ
   ৽͍͠໰୊΁ͷରॲͱͯ͠͸ɺ4/4ͰݟΒΕΔΤίʔνΣΠϯόʔ
   ݱ৅ʹΑΓ൓ରҙݟʹΞΫηε͢Δͷ͕೉͘͠ͳ͍ͬͯΔݱঢ়ʹରॲ͢
   ΔͨΊɺٞ࿦ʹର྆͠ۃੑͷҙݟΛநग़͢ΔɺͰ͋ͬͨΓɺTFYJTNత
   ͳ౤ߘͷର৅΍λΠϓʢܦݧஊͳͷ͔ྫ͑ͳͷ͔౳ʣ·Ͱਪఆ͢Δ΋ͷ
   ͳͲ
   

   View Slide

8. ঺հ͢Δ࿦จ
   "$PNQSFIFOTJWF"OBMZTJTPG1SFQSPDFTTJOHGPS8PSE
   3FQSFTFOUBUJPO-FBSOJOHJO"⒎FDUJWF5BTLT
   )FUFSPHFOFPVT(SBQI/FVSBM/FUXPSLTGPS&YUSBDUJWF
   %PDVNFOU4VNNBSJ[BUJPO
   ˞ଞͷ࿦จಡΈձͰ࿩ͨ͠಺༰ΛؚΈ·͢
   ײ৘ೝࣝͰҰൠతʹߦΘΕΔલॲཧͬͯຊ౰ʹҙຯ͋Δͷʁ࣮͸֐
   ΋͋ΔΜ͡Όͳ͍ʁͱ͍͏ٙ໰Λௐ΂ͨ
   )FUFSPHFOFPVTHSBQIΛ࢖ͬͯ୯ޠ΍จɺ֓೦ͷؔ܎ੑΛදݱ
   ֦ͨ͠ுੑͷߴ͍நग़తจॻཁ໿
   

   View Slide

9. "$PNQSFIFOTJWF"OBMZTJTPG1SFQSPDFTTJOH
   GPS8PSE3FQSFTFOUBUJPO-FBSOJOHJO"⒎FDUJWF5BTLT
   #abstract
   /BTUBSBO#BCBOFKBE %FQBSUNFOUPG&MFDUSJDBM&OHJOFFSJOHBOE$PNQVUFS4DJFODF
   FUBM "$-
   ಛʹײ৘ೝࣝܥͷλεΫʹ͓͍ͯલॲཧ͕୯ޠຒΊࠐΈʹ༩͑ΔӨڹΛௐ΂ɺ
   Α͘ߦΘΕΔ࣮ݧઃఆ͕ຊ౰ʹਖ਼͍͠ͷ͔ݕূ͢Δ
   ֶशࡁΈͷ୯ޠຒΊࠐΈΛ࢖͍͕͚ͪͩͲɺྫ͑͹ʮ޾ͤʯͱʮ൵͠Έʯͷ
   ϖΞ͕ʮ޾ͤʯͱʮتͼʯͷϖΞΑΓྨࣅ౓͕ߴ͘ͳΔΑ͏ͳຒΊࠐΈ͕ଘ
   ࡏ͢Δͷʹײ৘ೝ͕ࣝຊ౰ʹղ͚Δʁ
   4UPQXPSET OFHBUJPO 104 MFNNBUJ[BUJPOͳͲͷલॲཧΛͲ͏࢖͏͔
   ͕ຊ࣭తʹॏཁͳͷͰ͸ʁ
   લॲཧ͕୯ޠຒΊࠐΈʹ༩͑ΔӨڹͷେ͖͞Λݕূ͠ɺैདྷͷ࣮ݧઃఆͷݟ
   ௚͠Λߦ͍͍ͨ
   

   View Slide

10. #distributional hypothesis #word embedding
    ෼෍Ծઆʹجͮ͘୯ޠຒΊࠐΈͷݶք
    ʮ޾ͤʯͱʮ൵͠ΈʯͷϖΞ͕ʮ޾ͤʯͱʮتͼʯͷϖΞΑΓྨࣅ౓
    ͕ߴ͘ͳΔɺͳͲ௚ײʹ൓͢Δྨࣅ౓͕ಘΒΕΔ͜ͱ΋͋ΓɺλεΫ
    ͝ͱʹ୯ޠຒΊࠐΈΛௐ੔͢Δඞཁ͕͋Δ
    The Distributional Hypothesis is that words that occur in the
    same contexts tends to have similar meanings [Harris, 1954].
    ࣅͨจ຺Ͱසൟʹग़ݱ͢Δ୯ޠಉ࢜͸ҙຯతʹྨࣅ͍ͯ͠Δͱߟ͑ͯɺ
    ຒΊࠐΈۭؒͰ΋ۙ͘ͳΔͱ͍͏Ծઆ
    ୯ޠͷҙຯΛܾΊΔͨΊͷҰͭͷํ๏ͱͯ͠ɺ෼෍Ծઆ͕͋Δɻ
    ౷ܭతʹ୯ޠͷҙຯΛಘΔͨΊͷํ๏ͰɺXPSEWFDͷΑ͏ͳਪ࿦
    ϕʔεͷϞσϧ΍୯ʹ౷ܭ৘ใΛ࣍ݩ࡟ݮ͢ΔΧ΢ϯτϕʔεͷख๏΋
    ͋Δ
    

    View Slide

11. "$PNQSFIFOTJWF"OBMZTJTPG1SFQSPDFTTJOH
    GPS8PSE3FQSFTFOUBUJPO-FBSOJOHJO"⒎FDUJWF5BTLT
    #abstract
    λεΫݻ༗ͷඍௐ੔΍Ϟσϧͷվળ΋ॏཁͰ͸͋Δ͕ɺઌߦݚڀ͔Β͸લॲ
    ཧ΍ϋΠύʔύϥϝʔλͷӨڹ͕ແࢹͰ͖ͳ͍͜ͱ͕ಡΈऔΕΔ
    ֶश༻σʔλͷ୯ޠຒΊࠐΈΛߦ͏લɾޙͦΕͧΕͷλΠϛϯάͰલॲཧΛ
    ߦͬͨΓɺςετσʔλͷલॲཧͱ߹ΘͤͨΓ߹Θͤͳ͔ͬͨΓΛࢼ͢
    /BTUBSBO#BCBOFKBE %FQBSUNFOUPG&MFDUSJDBM&OHJOFFSJOHBOE$PNQVUFS4DJFODF
    FUBM "$-
    ಛʹײ৘ೝࣝܥͷλεΫʹ͓͍ͯલॲཧ͕୯ޠຒΊࠐΈʹ༩͑ΔӨڹΛௐ΂ɺ
    Α͘ߦΘΕΔ࣮ݧઃఆ͕ຊ౰ʹਖ਼͍͠ͷ͔ݕূ͢Δ
    

    View Slide

12. ؔ࿈ݚڀʢTFOUJNFOU FNPUJPOʣ
    • &NPUJPO$BVTF1BJS&YUSBDUJPO"/FX5BTLUP&NPUJPO
    "OBMZTJTJO5FYUT
    ◦ 3VJ9JB 4DIPPMPG$PNQVUFS4DJFODFBOE&OHJOFFSJOH
    FUBM "$-
    
    ◦ FNPUJPOͱDBVTFͷϖΞΛநग़͢Δ৽͍͠λεΫͷఏҊɻFNPUJPOͱ
    DBVTFͷϖΞͰϚϧνλεΫֶशΛߦ͏
    • /-'**5BU*&45&NPUJPO3FDPHOJUJPOVUJMJ[JOH/FVSBM
    /FUXPSLTBOE.VMUJMFWFM1SFQSPDFTTJOH
    ◦ 4BNVFM1FDBS 4MPWBL6OJWFSTJUZPG5FDIOPMPHZ
    FUBM &./-1
    ◦ 6TFSHFOFSBUFEDPOUFOUTΛ࢖༻͢Δ৔߹ͷલॲཧͷॏཁੑʹ͍ͭͯௐ΂
    ͍ͯΔɻಛʹإจࣈ΍ֆจࣈͷೝࣝΛৄ͘͠ߦ͍είΞΛ্͛Δ͜ͱʹ੒ޭ
    

    View Slide

13. ؔ࿈ݚڀʢXPSEWFD 6($ʣ
    • *NQSPWJOH%JTUSJCVUJPOBM4JNJMBSJUZXJUI-FTTPOTGSPN8PSE
    &NCFEEJOHT
    ◦ 0NFS-FWZ #BS*MBO6OJWFSTJUZ
    FUBM "$-
    ◦ 8PSEFNCFEEJOHʹ͓͍ͯɺΧ΢ϯτϕʔεͷख๏Ͱ΋ϋΠύʔύϥϝʔ
    λௐ੔࣍ୈͰXPSEWFDͳͲͷਪ࿦ϕʔεͷख๏ʹউͯΔ͜ͱΛࣔͨ͠
    ◦ ख๏΋ॏཁ͕ͩɺϋΠύʔύϥϝʔλͷٞ࿦΋ॏཁͱ͍͏͜ͱΛ໰୊ఏى
    • /-'**5BU*&45&NPUJPO3FDPHOJUJPOVUJMJ[JOH/FVSBM
    /FUXPSLTBOE.VMUJMFWFM1SFQSPDFTTJOH
    ◦ 4BNVFM1FDBS 4MPWBL6OJWFSTJUZPG5FDIOPMPHZ
    FUBM &./-1
    ◦ 6TFSHFOFSBUFEDPOUFOUTΛ࢖༻͢Δ৔߹ͷલॲཧͷॏཁੑʹ͍ͭͯௐ΂
    ͍ͯΔɻಛʹإจࣈ΍ֆจࣈͷೝࣝΛৄ͘͠ߦ͍είΞΛ্͛Δ͜ͱʹ੒ޭ
    ◦ લॲཧʹΧςΰϥΠζ͞ΕΔΑ͏ͳॲཧΛ͔ͬ͠Γ΍Δ͜ͱͰείΞ޲্ʹ
    ͭͳ͕Δͱ͍͏͜ͱ͕࿦จͰࣔ͞Εͨ
    #recent study #ugc #word2vec
    

    View Slide

14. ؔ࿈ݚڀʢલॲཧʣ
    • 0OTUPQXPSET pMUFSJOHBOEEBUBTQBSTJUZGPSTFOUJNFOU
    BOBMZTJTPGUXJUUFS
    ◦ )BTTBO4BJG 5IF0QFO6OJWFSTJUZ
    FUBM -3&$
    ◦ ετοϓϫʔυͷআڈ͕༗ޮ͔ͦ͏Ͱͳ͍͔͸ϫʔυϦετͷ࡞Γํ΍λε
    ΫͰେ͖͘ҟͳΔ͕ɺUXJUUFSTFOUJNFOUͰ͸Ұൠతͳํ๏ͩͱ֐ͷํ͕େ
    ͖͍͜ͱΛࣔͨ͠
    ◦ Ұൠతͳલॲཧख๏ΛφΠʔϒʹద༻͢Δ͚ͩͰ͸͍͚ͳ͍͜ͱ͕͋Δ͜ͱ
    Λࣔͨ͠
    • "DPNQBSBUJWFFWBMVBUJPOPGQSFQSPDFTTJOHUFDIOJRVFTBOE
    UIFJSJOUFSBDUJPOTGPSUXJUUFSTFOUJNFOUBOBMZTJT
    ◦ 4ZNFPO4ZNFPOJEJT &YQFSU4ZTUFNTXJUI"QQMJDBUJPOT
    ◦ લॲཧͷςΫχοΫΛ৭ʑࢼͯ͠ΈͨΒɺײ৘෼ੳͰ͸MFNNBUJ[BUJPOͱ
    ਺ࣈͷআڈɺ୹ॖܗͷஔ׵͕࠷΋είΞʹد༩
    ◦ ෼ྨσʔλͷલॲཧʹؔͯ͠แׅతͳείΞධՁΛߦͬͨ
    #recent study #preprocessing #emotion
    

    View Slide

15. #key points
    ͜ͷ࿦จΛ঺հ͢Δཧ༝
    ໘ന͍৽نख๏΋ͨ͘͞Μ͋Δ͕ɺ࣮ӡ༻Ͱਫ਼౓͕ग़ͤΔ΋ͷ͕ͳ͔
    ͳ͔ͳ͍ͱײ͍ͯͨ͡
    ݁ہલॲཧͷબͼํ΍ख๏ͷҧ͍͕େ͖͘είΞʹӨڹ͍ͯ͠Δ͕ɺ
    ࿦จͰͦΕΛ࿦͍ͯ͡Δ΋ͷ͕΄ͱΜͲͳ͍
    ҉໧஌తͳલॲཧͷ஌ࣝΛ·ͱΊΔ͍͍ػձʹͳΕ͹͍͍͔ͳͱࢥͬ
    ͨ
    

    View Slide

16. #key points
    ΍ͬͨ͜ͱ
    લॲཧΛ୯ޠຒΊࠐΈʹ౷߹͢ΔͱͲΜͳޮՌ͕͋Δ͔ʁ
    Ͳͷલॲཧ͕ײ৘෼ੳܥͷλεΫʹޮՌ͕͋Δͷ͔ʁ
    ࣄલֶश͞Εͨ΋ͷΑΓվળ͞Ε͍ͯΔ͔ʁ
    ͭͷֶशσʔλɺͭͷςετσʔλΛ࢖༻ͨ͠ײ৘ܥλεΫͰɺֶ
    शσʔλɺ෼ྨσʔλɺ྆ํɺͦΕͧΕʹલॲཧΛద༻ͨ͠৔߹Ͱൺ
    ֱ
    ݕূͨ͜͠ͱ
    

    View Slide

17. #preprocessing #pipeline
    /-1ʹ͓͚ΔલॲཧͷྲྀΕ
    ΫϦʔχϯά
    ෼ׂ
    ਖ਼نԽ
    ѹॖ
    ϕΫτϧԽ
    λά ه߸ͳͲͷআڈ QVODUVBUJPO
    ܗଶૉղੳ ࣙॻͷ௥Ճ ܎Γड͚ղੳ
    ਺ࣈͷஔ͖׵͑ إจࣈͳͲͷೝࣝ TQFMMDIFDL
    දهΏΕ MPXFSDBTJOH ୅දޠ΁ͷஔ͖׵͑ লུޠ
    MFNNBUJ[BUJPO TUFNNJOH OFHBUJPO Φϯτϩδʔ
    4UPQXPSEͷআڈ 104
    $#08 TLJQHSBN #&35
    DPWFSBHFͷௐࠪ ෼ྨσʔλͱޠኮΛ͚ۙͮΔ FUD
    

    View Slide

18. #preprocessing #negation
    /FHBUJPO
    • ൓ҙޠࣙॻͷ࡞੒
    ◦8PSE/FUίʔύεͰ൓ҙޠࣙॻΛ࡞੒
    ◦൓ҙޠ͕ݟ͔ͭΒͳ͍PSͭͰ͋Ε͹ͦͷ··ɺෳ਺͋Δ৔߹͸
    VL8BDίʔύεͷதͰ࠷େͷස౓Λ࣋ͭ൓ҙޠͱͨ͠Γ୯ʹϥϯμϜ
    ʹબ୒ͨ͠Γ
    • ൱ఆޠͷ൓ҙޠ΁ͷஔ׵
    ◦൱ఆޠ͕ݟ͔ͭͬͨ৔߹ɺଓ͘୯ޠΛநग़͠ɺ൓ҙޠࣙॻͰ൓ҙޠΛ
    ݕࡧɻ൓ҙޠ͕ݟ͔ͭͬͨ৔߹ɺ൱ఆޠͱ൱ఆ͞ΕͨޠΛͦΕʹஔ͖
    ׵͑Δ
    ◦ྫ͑͹ɺͱ͍͏จͰ͸ɺ൱ఆޠʢ`OPUʣ
    ͱͦΕʹରԠ͢Δ୯ޠʢIBQQZʣΛಛఆɻ൓ҙޠࣙॻͰbIBQQZ`ͷ൓
    ҙޠʢ`TBE`ʣΛ୳͠ɺOPUIBQQZ`ΛbTBE`ʹஔ͖׵͑Δ
    

    View Slide

19. #corpus #training #dataset
    /FXT
    શମͱͯ͠ɺ4UPQXPSEͷআڈ΍104Ͱ͸WPDBCTJ[F͸͋·Γม
    ΘΒͳ͍͕DPSQVTTJ[F͕େ͖͘ݮগ
    ʙ೥ͷΞϝϦΧͷͷग़
    ൛෺͔Βͷ ݅ͷهࣄ
    8JLJQFEJB
    8JLJQFEJBͷهࣄ ݅Ͱ
    ߏ੒͞ΕΔɺ/FXTΑΓ໿ഒେ͖
    ͍ίʔύε
    5SBJOJOH$PSQVT
    ͭͷαΠζɾੑ࣭ͷҟͳΔίʔύεʹͭͷલॲཧΛߦ͏
    

    View Slide

20. #corpus #evaluation #dataset
    &WBMVBUJOH$PSQVT
    4FOUJNFOUBOBMZTJT FNPUJPODMBTTJpDBUJPO
    TBSDBTNEFUFDUJPOͷͭͷλεΫͰධՁɻ
    • *.%#
    ◦ ݅ͷөըϨϏϡʔɻϙδωΨൺ
    • 4FN&WBM
    ◦ ໿πΠʔτɻϙδωΨൺ
    • "JSMJOF
    ◦ ߤۭձࣾࣾʹؔ͢Δ໿݅πΠʔτɻ
    4FOUJNFOUBOBMZTJTײ৘ϙδωΨ
    • *4&"3
    ◦ ໿݅ͷɺײ৘Λשى͢Δݸਓతͳ࿩
    • "MN
    ◦ ໿݅ͷ͓ͱ͗࿩
    • 44&$
    ◦ 4FN&WBMΛ࠶Ξϊςʔγϣϯͨ͠໿݅ͷπ
    Πʔτ
    &NPUJPO%FUFDUJPOײ৘Ϋϥε෼ྨ 4BSDBTN%FUFDUJPOൽ೑ͷݕग़
    • 0OJPO
    ◦ ൽ೑Λѻ͏ϝσΟΞͱͦ͏Ͱͳ͍ϝσΟΞ͔Βऩू
    ͨ͠໿݅ͷχϡʔεϔουϥΠϯ
    • *"$
    ◦ ໿݅ͷൃ࿩Ԡ౴
    • 3FEEJU
    ◦ ஶऀ͕ϥϕϧ෇͚ͨ͠໿ສ݅ͷ3FEEJU౤ߘ
    

    View Slide

21. #result
    /FHBUJPO͕શͯͷσʔληοτʹ͓͍ͯ࠷΋ޮՌతͩͬͨ
    /FXTίʔύεʹલॲཧΛߦͬͨ͋ͱ୯ޠຒΊࠐΈΛ࡞੒ͨ͠৔߹ͷGTDPSF
    /FHBUJPOҎ֎ͷલॲཧͷෳ߹ΛؚΊͯ΋ɺOFHBUJPOͷΈͷ৔߹͕ৗʹ
    ൪໨ʹείΞ͕ߴ͔ͬͨ
    ୯७ʹલॲཧΛॏͶͯ΋ৗʹޮՌ͕͋Δͱ͸ݶΒͳ͍
    

    View Slide

22. #result
    ʢҰൠతͳʣ4UPQXPSET TUFNNJOH͸ɺ୯ମͰ͸ҙຯ͕͋Γͦ͏ʹݟ͑
    ͯ΋ଞͷલॲཧͱಉ࣌ͩͱείΞʹد༩͍ͯ͠ͳ͍͜ͱ͕Θ͔Δ
    શͯͷલॲཧΛద༻ͯ͠΋OFHBUJPOͷΈͷ৔߹ͱมΘΒͳ͍͔গ͠Լ͕Δ
    ͘Β͍ʢ0OJPO 3FEEJU 44&$ʣ
    4UPQXPSET΍104͸ίʔύεαΠζΛେ͖͘ݮগͤ͞Δ͕ɺ104Ͱ͸
    είΞݮগ͕ͳ͍
    

    View Slide

23. #result
    XJLJQFEJBDPSQVTΛ࢖ͬͨ$#08 4LJQHSBN #&35ͷ'TDPSFൺֱ
    8JLJQFEJBͰ΋ಉ༷ͷ܏޲͕ΑΓڧ·ͬͨ
    

    View Slide

24. #result #preprocess #postprocess
    ֶशίʔύεʹલॲཧΛద༻͢Δ৔߹ʢQSFʣͱɺ
    ෼ྨσʔληοτʹલॲཧΛద༻͢Δ৔߹ʢQPTUʣͷൺֱ
    ௚ײ௨ΓɺQPTUͷΈ͕͍ͣΕͷ৔߹Ͱ΋࠷΋είΞ͕௿͘ͳͬͨ
    QSFͱCPUIͰείΞʹେ͖ͳ͕ࠩͳ͘ɺQSF͕࠷΋ॏཁͰ͋Δ͜ͱ͕ࣔ
    ͞Εͨ
    Ұൠతʹɺ୯ޠຒΊࠐΈ͕༩͑ΒΕͨ৔߹͸෼ྨσʔλΛ߹Θͤʹ͍͘͜ͱ
    ͕ଟ͍Α͏ʹࢥ͏ͷͰɺҙ֎ͳ݁Ռ
    

    View Slide

25. #result #compare with SoTA
    4P5"ϕʔεϥΠϯʹର͢ΔఏҊϞσϧͷධՁ
    શͯͷλεΫͰఏҊख๏܈͕4P5"Λ্ճΔ
    #&35͕Ұ൪ڧ͍ͷ͸౰વͳͷͰগͣ͠Δ͍͕ɺఏҊख๏શମͱͯ͠উͬͯ
    ͍Δ΋ͷ͕ଟ͍ʢ*.%# *"$ 0OJPO 3FEEJU 44&$ʣ
    4P5"ͳࣄલֶशϞσϧ͸ఏҊख๏ΑΓང͔ʹେ͖͍ίʔύεΛ࢖͍ͬͯΔ
    ͷͰɺQSFͷॏཁੑ͕Θ͔Δ
    

    View Slide

26. #result #relative improvement
    GTDPSFͷઈର஋ͱجຊతͳલॲཧ͔Βͷ૬ରతͳվળ
    TFOUJNFOUBOBMZTJTͱTBSDBTNEFUFDUJPOͷͭͷόΠφϦλεΫΑ
    ΓϚϧνΫϥε෼ྨλεΫͰͷվળ෯ͷ΄͏͕एׯେ͖͍
    ΑΓଟ͘ͷσʔληοτͰൺֱ͠ͳ͍ͱ·ͩ·ͩඍົͳࠩͰ͔͠ͳ͍Α͏ͳ
    ؾ͸͢Δ
    

    View Slide

27. #key points
    ·ͱΊ
    ୯ޠຒΊࠐΈ࣌఺Ͱͷલॲཧ͕࠷΋λΠϛϯάͱͯ͠༗ޮͰ͋Δ͜ͱ
    ͕ࣔ͞Εͨ
    ୯ମͱͯ͠͸OFHBUJPO͕࠷΋ޮՌ͕͋ΓɺҰൠతͳTUPQXPSET
    ΍TUFNNJOH͸είΞΛԼ͛Δ͜ͱ͕ଟ͍
    ڊେͳίʔύεͰֶशࡁΈͷ୯ޠຒΊࠐΈΛ࢖͏ΑΓɺλεΫʹ߹Θ
    ͤͨલॲཧΛద੾ͳλΠϛϯάͰߦ͏͜ͱͰείΞͰ্ճΕΔ
    ҉໧஌తʹ஌ΒΕ͍ͯͨ஌ݟ͕ଟ͍͕ɺ͔ͬ͠Γͨ͠ݕূΛߦ͏͜ͱ
    Ͱମܥతͳ஌ࣝʹͨ͠
    ਖ਼௚·ͩ·࣮ͩݧ͕଍Γ͍ͯͳ͍෦෼΋͋Δͱײ͕ͨ͡ɺΑΓแׅత
    ͳ࣮ݧΛ͢Δ͜ͱͰ͔ͳΓ໘ന͘ͳΓͦ͏
    

    View Slide

28. ঺հ͢Δ࿦จ
    "$PNQSFIFOTJWF"OBMZTJTPG1SFQSPDFTTJOHGPS8PSE
    3FQSFTFOUBUJPO-FBSOJOHJO"⒎FDUJWF5BTLT
    )FUFSPHFOFPVT(SBQI/FVSBM/FUXPSLTGPS&YUSBDUJWF
    %PDVNFOU4VNNBSJ[BUJPO
    ˞ଞͷ࿦จಡΈձͰ࿩ͨ͠಺༰ΛؚΈ·͢
    ײ৘ೝࣝͰҰൠతʹߦΘΕΔલॲཧͬͯຊ౰ʹҙຯ͋Δͷʁ࣮͸֐
    ΋͋ΔΜ͡Όͳ͍ʁͱ͍͏ٙ໰Λௐ΂ͨ
    )FUFSPHFOFPVTHSBQIΛ࢖ͬͯ୯ޠ΍จɺ֓೦ͷؔ܎ੑΛදݱ
    ֦ͨ͠ுੑͷߴ͍நग़తจॻཁ໿
    

    View Slide

29. )FUFSPHFOFPVT(SBQI/FVSBM/FUXPSLT
    GPS&YUSBDUJWF%PDVNFOU4VNNBSJ[BUJPO
    #abstract
    จॻཁ໿Ͱ͸ɺηϯςϯεؒͷؔ܎ੑͷϞσϧԽ͕
    ඇৗʹॏཁɻैདྷ͸ɺ3//ϕʔεͷख๏ͰܥྻͰ
    ϞσϧԽ͍ͯͨ͠
    %BORJOH8BOH 4IBOHIBJ,FZ-BCPSBUPSZPG*OUFMMJHFOU*OGPSNBUJPO1SPDFTTJOH 'VEBO6OJWFSTJUZ
    FUBM "$-
    நग़తจॻཁ໿Ͱηϯςϯεؒͷؔ܎ੑΛදݱ͢ΔͨΊʹ
    IFUFSPHFOFPVTHSBQIΛಋೖ͠ɺ4P5"Λୡ੒֦ுੑͳͲʹ͍ͭͯݕূͨ͠ɻ
    จॻͷҙຯߏ଄͸ܥྻΑΓάϥϑߏ଄ͷํ͕దͯ͠
    ͍Δ͜ͱ͕࠷ۙͷݚڀͰΘ͔͖͍ͬͯͯΔ͕ɺྑ͍
    άϥϑߏ଄͸·ͩఏҊ͞Ε͍ͯͳ͔ͬͨ
    ୯ޠϊʔυͱจϊʔυΛ࣋ͭIFUFSPͳHSBQIߏ
    ଄ΛఏҊ͠ɺ୯จॻɾଟจॻཁ໿ͦΕͧΕͰ
    4P5"Λୡ੒ɻ֦ுੑʹ͍ͭͯ΋ٞ࿦ͨ͠
    

    View Slide

30. #abstract #extractive document summarization
    ݩͷจॻ͔Βؔ࿈͢ΔจॻΛऔΓग़ͯ͠ɺཁ໿
    ͱͯ͠࠶ߏ੒͢ΔλεΫ
    நग़తจॻཁ໿
    ୯ޠΛܦ༝ͨ͠จͷؔ܎ੑΛදݱ͢ΔIFUFSPHSBQIΛఆٛ
    υΩϡϝϯτͷ֤ηϯςϯεΛ#JEJSFDUJPOBM-45.ͰϕΫτϧԽɻ͜Ε
    ʹΑͬͯηϯςϯεͷҙຯΛଊ͑ͨϕΫτϧ͕࡞ΒΕΔʢXPSEMBZFSʣ
    நग़ܕͱɺදݱΛந৅Խͯ͠θϩ͔Βཁ໿จΛ
    ࡞Δੜ੒ܕɺͦΕΒͷࠞ߹ͷύλʔϯ͕͋Δ
    ͞Βʹ͜ͷϕΫτϧಉ࢜ͷؔ܎ੑΛ#JEJSFDUJPOBM-45.Ͱֶश͢Δ
    ʢTFOUFODFMBZFSʣ
    ηϯςϯεΛநग़͢Δ֬཰Λग़ྗ
    4VNNB3V//FS
    ॳظͷݚڀ
    

    View Slide

31. )FUFSPHFOFPVT(SBQI
    ࣮ੈքͷάϥϑ͸IFUFSPHFOFPVTͳ΋ͷ͕ଟ͍
    ࣮ੈքͷάϥϑ͸ɺҟͳΔಛ௃ۭؒͷ༷ʑͳλΠϓͷϊʔυɾΤοδͰ
    ߏ੒͞Ε͍ͯΔ
    #abstract #heterogeneous graph
    

    View Slide

32. #model overview
    ηϯςϯεͷΈΛϊʔυͱͯ͠άϥϑΛߏங͢
    ΔͷͰ͸ͳ͘ɺηϯςϯεΛͭͳ͙஥հ໾ͷΑ
    ͏ͳϊʔυΛ௥Ճ
    1SPQPTFE(SBQI
    ୯ޠΛܦ༝ͨ͠จͷؔ܎ੑΛදݱ͢ΔIFUFSPHSBQIΛఆٛ
    จ৘ใͰ୯ޠϊʔυΛߋ৽Ͱ͖Δ ଞͷϊʔυλ
    ΠϓΛ௥Ճ͢ΔͳͲͷ֦ுੑ͕͋ΔɺͳͲͷར
    ఺
    ͜ͷ࿦จͰ͸ɺ࠷খҙຯ୯ҐΛ୯ޠʹ͍ͯ͠
    Δɻྫ͑͹ɺΑΓந৅Խͯ͠୯ޠͷҙຯ΍֓೦
    ΛϊʔυλΠϓͱ͢Δ͜ͱ΋໘നͦ͏
    HSBQIJOJUJBMJ[Fˠ("5Ͱߋ৽ˠηϯςϯε
    ಛ௃͔Βཁ໿จʹ௥Ճ͢Δ͔൱͔ͷ෼ྨ໰୊Λ
    ղ͘ɺͱ͍͏खॱ
    

    View Slide

33. #model overview #learning step
    HSBQIJOJUJBMJ[FSͰɺจʹΧʔωϧαΠζͷҟ
    ͳΔ$//Λద༻ͯ͠OHSBNಛ௃Λநग़ʢہ
    ॴಛ௃ʣɺ࣍ʹ#J-45.ͰηϯςϯεϨϕϧͷ
    ಛ௃Λநग़ʢେҬಛ௃ʣ
    1SPQPTFE(SBQI
    ֶशखॱͱNPEFMPWFSWJFX
    ୯ޠϊʔυͱจϊʔυͷؔ܎ੑʹؔ͢Δ৘ใͱ
    ͯ͠ɺUGJEGΛΤοδಛ௃Ͱ࢖༻͢Δ
    άϥϑಛ௃͸(SBQI"UUFOUJPO/FUXPSLͰ
    ߋ৽
    

    View Slide

34. #model overview #graph attention network
    ࣗ਎ͱपғʹͦΕͧΕॏΈΛ͔͚ͨϕΫτϧ͔ΒBUUFOUJPOΛܭࢉ
    ͠ɺपลϊʔυ͔ΒͷBHHSFHBUJPOʹར༻
    (SBQI"UUFOUJPO/FUXPSL
    άϥϑ্ͰͷBUUFOUJPOΛఆٛ
    "UUFOUJPO
    ྡ઀ϊʔυ
    "UUFOUJPOΛܭࢉ͢Δؔ਺
    "UUFOUJPOΛߟྀͨ͠
    BHHSFHBUJPO
    άϥϑू໿ͷڑ཭ؔ਺Λɺάϥϑߏ଄ʹґଘ͠ͳ͍BUUFOUJPOͱͯ͠
    ఆֶٛ͠शϕʔεͰٻΊΔɺΈ͍ͨͳ࿩
    ϊʔυಛ௃
    

    View Slide

35. #dataset #train test split
    %BUBTFU
    ୯จॻཁ໿Ͱ͸ͭɺෳ਺จॻཁ໿Ͱ͸ͭͷσʔληοτͰ࣮ݧ
    • ୯จॻཁ໿Ͱ࠷΋޿͘ར༻͞Ε͍ͯΔϕϯνϚʔΫσʔληοτ
    • USBJO WBMJE UFTUσʔλ͸ͦΕͧΕ
    $//%BJMZ.BJM2"σʔλ
    • /FX:PSL5JNFT"OOPUBUFE$PSQVT 4BOEIBVT
    ͔Βऩू͞Εͨ୯จॻཁ໿
    σʔληοτ
    • USBJO WBMJE UFTUσʔλ͸ͦΕͧΕ ݅
    /:5
    .VMUJ/FXT
    • ෳ਺จॻཁ໿σʔληοτ
    • ͦΕͧΕʙͷจॻʹର͠ɺਓ͕ؒॻ͍ͨཁ໿͕͋Δ
    • USBJO WBMJE UFTUσʔλ͸ͦΕͧΕ
    

    View Slide

36. #experiment #setting #hyper-parameter #preprocessing
    4FUUJOH)ZQFSQBSBNFUFST
    લॲཧ
    άϥϑ
    ࣮ݧ
    ετοϓϫʔυ΍۟ಡ఺ͷআڈ ೖྗจॻͷ࠷େ௕Λจʹ
    ઃఆ UGJEGԼҐΛআڈ ޠኮ਺Λʹ੍ݶ
    ࣍ݩͷ(MP7FͰຒΊࠐΈ
    จϕΫτϧαΠζ͸ͰॳظԽ Τοδಛ௃ྔ
    ࣍ݩ͸ͰॳظԽ IFBE
    όοναΠζ ֶश཰F "EBN FQPDIͰMPTT
    ͕Լ͕Βͳ͍৔߹FBSMZTUPQQJOH ୯จॻཁ໿Ͱ͸্Ґจ
    ෳ਺จॻཁ໿Ͱ͸্ҐจΛબ୒
    

    View Slide

37. #methods #extractor
    • &YU#J-45.
    ◦$//૚#J-45.
    ◦จॻΛจͷܥྻͱΈͳ͠จؔ܎Λֶश͢Δ
    • &YU5SBOTGPSNFS
    ◦5SBOTGPSNFS૚USBOTGPSNFS
    ◦શจͷϖΞϫΠζ૬ޓ࡞༻Λֶश
    ◦จϨϕϧͷ׬શ࿈݁άϥϑͱΈͳͤΔ
    • )4( )FUFS4VN(SBQI
    
    ◦ఏҊख๏ɻจ୯ޠจͷؔ܎ੑΛάϥϑͰϞσϧԽ
    ◦)4(Ͱ͸ϊʔυ෼ྨʹΑͬͯཁ໿จΛબ୒͠ɺ͞ΒʹUSJHSBN
    CMPDLJOHʹΑͬͯUSJHSBN͕ࣅ͍ͯΔจΛআ֎͠৑௕ੑΛ཈͑ͨόʔ
    δϣϯ΋࣮ݧ
    .FUIPET
    

    View Slide

38. #result #CNN/DailyMail
    3FTVMUʢ୯จॻཁ໿ɿ$//%BJMZ.BJMʣ
    $//%BJMZ.BJMͰͷ୯จॻཁ໿ͷ݁Ռɻطଘख๏͢΂ͯΛ্ճΔείΞ͕ಘΒΕͨɻ
    -&"%͕ϕʔεϥΠϯɺ
    03"$-&͕VQQFSCPVOE
    MBCFM
    
    QSFWJPVTTUVEZ
    QSPQPTFENFUIPE
    จ຺όϯσΟου໰୊ͱͯ͠ఆٛ
    ͨ͠)&3ʹؔͯ͠͸ಛʹϙϦ
    γʔ͋Γͳ͠΋࣮ݧ͠ɺ͍ͣΕ
    ΋উͪ
    ʢ#&35Λ࢖͍ͬͯͳ͍ʣશͯͷطଘख๏ΑΓߴ͍είΞ͕ಘΒΕͨ
    306(& -ͰධՁɻͦΕ
    ͧΕHSBN HSBN Ұக͢Δ
    ࠷௕ܥྻͷྨࣅ౓ͷείΞ
    

    View Slide

39. #result #CNN/DailyMail
    3FTVMUʢ୯จॻཁ໿ɿ$//%BJMZ.BJMʣ
    จܥྻ΍׬શ઀ଓάϥϑΛར༻ͨ͠ख๏ͱൺ΂Δ͜ͱͰɺ
    IFUFSPHSBQIߏ଄ͷ༗༻ੑ͕ࣔ͞Εͨɻ
    &YUNFUIPE
    QSPQPTFENFUIPE
    จܥྻ΍ɺ׬શ઀ଓάϥϑΛ࢖ͬ
    ͨ&YU#J-45. &YU
    5SBOTGPSNFSΑΓߴ͍είΞ
    IFUFSPHSBQIΛ࢖͏͜ͱͰɺ
    ηϯςϯεؒͷෆཁͳ݁߹ΛޮՌ
    తʹআڈͰ͖͍ͯΔ
    

    View Slide

40. #result #NYT50
    3FTVMUʢ୯จॻཁ໿ɿ/:5ʣ
    /:5Ͱͷ୯จॻཁ໿ͷ࣮ݧ݁Ռɻ$//%BJMZ.BJMͱجຊతʹಉ͡܏޲͕ݟΒΕͨɻ
    جຊతʹ$//%BJMZ.BJM
    ͱಉ͡ͰɺఏҊख๏͕طଘ
    ख๏Λ্ճ͍ͬͯΔ
    QSPQPTFENFUIPE
    USJHSBNCMPDLJOH͋Γ
    όʔδϣϯ͕ҐͰ͸ͳ͍
    ͷ͸ͳͥɾɾɾʁ
    ˠ$//%BJMZ.BJMͰ͸ॏෳͷ
    গͳ͍Օ৚ॻ͖Λ࿈݁͢Δܗࣜ
    ͕ͩɺ/:5Ͱ͸Ωʔϑ
    Ϩʔζ͕ෳ਺ճొ৔͢ΔͳͲॏ
    ෳ͕͋ΔɻͳͷͰɺUSJHSBN
    CMPDLJOHͰ͸/:5Ͱε
    ίΞΛग़ͮ͠Β͍ͷͰ͸
    

    View Slide

41. #ablation #CNN/DailyMail
    ୯ޠϑΟϧλϦϯάͷ࡟আͰ
    3 3-͸είΞݮগ 3
    ͸είΞ૿Ճ
    "CMBUJPO
    $//%BJMZ.BJMͰBCMBUJPO͠Ϟδϡʔϧͷߩݙ౓Λௐ΂ͨɻ
    ୯ޠϑΟϧλϦϯάʹΑΓɺಛʹॏཁͳ୯ޠϊʔυʹϑΥʔΧεͰ͖Δར఺
    ͕CJHSBN৘ใΛࣦ͏σϝϦοτΛ্ճ͍ͬͯΔͷͰ͸ͳ͍͔
    ("5૚ؒͷSFTJEVBM
    DPOOFDUJPOΛ࡟আ͢Δ͜ͱͰ
    είΞ͕େ͖͘ݮগ
    ("5૚ͷSFTJEVBMDPOOFDUJPO͸ɺIFUFSPHSBQIʹ͓͚ΔผλΠϓͷ
    ϊʔυ͔Βͷू໿Ͱཧ࿦తʹॏཁͳͷͰ୯ͳΔ݁߹Ͱ͸ஔ͖׵͑Ͱ͖ͳ͍
    

    View Slide

42. #result #multidocument
    )4( )%4(ڞʹطଘख๏Λ্ճ
    ΔείΞ͕ಘΒΕ͍ͯͯɺಛʹ
    )%4(ͰείΞ্ঢ͕େ͖͍
    3FTVMUʢଟจॻཁ໿ʣ
    ଟจॻཁ໿Ͱ΋จॻϊʔυΛ௥Ճͨ͠ఏҊख๏Ͱݕূ
    จॻϊʔυͷ௥Ճ͕ଟจॻཁ໿ʹ
    ޮՌతͰ͋Δ͜ͱ͕ࣔࠦ
    USJHSBNCMPDLJOH͕ޮ͍͍ͯͳ͍
    ͷ͸ɺ͓ͦΒ͖ͬ͘͞ͱಉ͡ཧ༝
    ఏҊख๏Ͱ͸୯ʹϊʔυλΠϓΛ௥Ճ͢Δ͚ͩͰผλεΫʹԠ༻Ͱ͖͓ͯ
    Γɺൃలੑ͕ߴ͍
    QSPQPTFENFUIPE
    

    View Slide

43. #qualitative analysis #degree
    ୯ޠϊʔυͷ౓਺͕ߴ͍ͱɺͦͷ୯ޠ
    ͷग़ݱ਺͕ଟ͍ͱ͍͏͜ͱʹͳΓจॻ
    ͷ৑௕౓Λʢଟগʣද͢
    2VBMJUBUJWF"OBMZTJT
    ୯ޠϊʔυͷ౓਺͕༩͑ΔӨڹΛௐࠪ
    ୯ޠϊʔυ͕͋Δ͜ͱͰɺจ৘ใͷू໿ͱେҬදݱͷ఻೻͕ߦΘΕ͍ͯΔՄ
    ೳੑ͕ࣔࠦ͞ΕΔ
    ୯ޠͷ౓਺ͱ306(&͕ൺྫ
    ˠ৑௕ੑͷߴ͍จॻ΄Ͳཁ໿͠қ͍
    ౓਺͕ߴ͍ͱෳ਺ͷจͷ৘ใΛू໿͢
    Δ͜ͱ͕Ͱ͖ɺϞσϧͷԸܙΛΑΓڧ
    ͘ड͚Δ͜ͱ͕Ͱ͖Δͱߟ͑ΒΕΔ
    

    View Slide

44. #qualitative analysis #source
    จॻ͕૿Ճ͢Δ͜ͱͰɺϕʔεϥΠϯ
    ͸্ঢ͢Δ͕ఏҊख๏Ͱ͸௿Լ͠
    จͰฒͿ
    2VBMJUBUJWF"OBMZTJT
    ଟจॻཁ໿Ͱɺจॻͷ਺ͷӨڹΛௐࠪ
    จॻ਺ͷ૿ՃͰ)&5&346.(3"1)ͱ)&5&3%0$46.(3"1)ͷੑ
    ೳ͕֦ࠩେจॻͱจॻͷؔ܎͕ෳࡶʹͳΔ΄Ͳɺจॻϊʔυͷར఺͕Α
    Γେ͖͘ͳΔ
    'JSTU͸ɺΧόϨοδΛ֬อͰ͖Δ
    จষΛ֤จॻ͔Βڧ੍తʹநग़Ͱ͖Δ
    จॻ਺ͷ૿Ճʹ൐͍ɺશจͷओࢫΛΧ
    όʔͰ͖ΔݶΒΕͨ਺ͷจΛநग़͢Δ
    ͜ͱ͕ࠔ೉ʹͳ͍ͬͯͨ͘Ί
    

    View Slide

45. #key points
    ·ͱΊ
    IFUFSPHSBQIΛ࢖͏͜ͱͰɺจॻཁ໿ʹpOFHSBJOFEͳҙຯ୯Ґ
    Λಋೖ͢Δ͜ͱ͕Ͱ͖ɺจɾจষؒͷؔ܎ੑͷϞσϦϯά΁ͷ༗ޮੑ
    ͕͔֬ΊΒΕͨ
    ख๏ͷ֦ுੑ͸ߴ͘ɺ୯จॻཁ໿͔ΒϊʔυλΠϓͷ௥ՃͷΈͰଟจ
    ॻཁ໿ʹରԠՄೳ
    IFUFSPHSBQIʹಛԽͨ͠ख๏ʢϝλύεΛ࢖ͬͨαϒάϥϑͷఆ
    ٛɺIFUFSPHSBQIʹର͢ΔBUUFOUJPO౳ʣΛࢼ͢ͱ໘ന͍͔΋
    ࠓޙ͸#&35౳ࣄલֶशϞσϧΛ͍Ζ͍Ζݕ౼͍ͨ͠ͱͷ͜ͱ
    චऀ΋ܰ͘৮Ε͍͕ͯͨɺ୯ޠϊʔυʹ౰ͨΔ෦෼͕ҙຯϊʔυ·Ͱ
    ந৅Խ͞ΕͨΓͨ͠Βख๏ͷ༏Ґੑ͕ΑΓ׆͔͞ΕΔͱࢥ͏ɻͦ͏Ͱ
    ͳͯ͘΋ɺϊʔυλΠϓͷ௥Ճ͸͍Ζ͍Ζࢼͤͦ͏
    

    View Slide