Upgrade to Pro — share decks privately, control downloads, hide ads and more …

ACL2020 Category Survey: Sentiment Analysis

uchi_k
October 18, 2020

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。

uchi_k

October 18, 2020
Tweet

More Decks by uchi_k

Other Decks in Programming

Transcript

  1. ಺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
  2. Sentiment Analysis ͦͷଞ  ൺֱબ޷෼ྨ  ཁ໿  આಘྗղੳ 

    ελϯεݕग़  લॲཧ  ΞεϖΫτࣝผ  ײ৘ݪҼϖΞநग़  ΞεϖΫτϕʔεײ৘෼ྨ  ϨϏϡʔίϝϯτ౳ͷ VTFSHFOFSBUFE DPOUFOUT 6($ ͷϚΠ χϯά͕ଟ͘ɺ࢈ۀԠ༻ ࢤ޲ͷݚڀ͕ଟ͍෼໺ 6($ͷղੳ͸঎඼ͷΧς ΰϦ΍࢖༻ঢ়گ͋Γ͖ͷ ײ৘ೝࣝʹͳΔ͜ͱ͕ଟ ͍ˠΞεϖΫτϕʔεײ ৘෼ྨͷ࿦จ͕ଟ͍
  3. "$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
  4. #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
  5. ؔ࿈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੒ޭ
  6. ؔ࿈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
  7. ؔ࿈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
  8. #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
  9. #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 ◦ྫ͑͹ɺ<b* BN OPU IBQQZ bUPEBZ`>ͱ͍͏จͰ͸ɺ൱ఆޠʢ`OPUʣ ͱͦΕʹରԠ͢Δ୯ޠʢIBQQZʣΛಛఆɻ൓ҙޠࣙॻͰbIBQQZ`ͷ൓ ҙޠʢ`TBE`ʣΛ୳͠ɺOPUIBQQZ`ΛbTBE`ʹஔ͖׵͑Δ
  10. #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$PSQVT ͭͷαΠζɾੑ࣭ͷҟͳΔίʔύεʹͭͷલॲཧΛߦ͏
  11. #corpus #evaluation #dataset &WBMVBUJOH$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
  12. )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΋ٞ࿦ͨ͠
  13. #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
  14. #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
  15. #model overview #graph attention network ࣗ਎ͱपғʹͦΕͧΕॏΈΛ͔͚ͨϕΫτϧ͔ΒBUUFOUJPOΛܭࢉ ͠ɺपลϊʔυ͔ΒͷBHHSFHBUJPOʹར༻ (SBQI"UUFOUJPO/FUXPSL άϥϑ্ͰͷBUUFOUJPOΛఆٛ "UUFOUJPO

    ྡ઀ϊʔυ "UUFOUJPOΛܭࢉ͢Δؔ਺ "UUFOUJPOΛߟྀͨ͠ BHHSFHBUJPO άϥϑू໿ͷڑ཭ؔ਺Λɺάϥϑߏ଄ʹґଘ͠ͳ͍BUUFOUJPOͱͯ͠ ఆֶٛ͠शϕʔεͰٻΊΔɺΈ͍ͨͳ࿩ ϊʔυಛ௃
  16. #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     
  17. #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୒
  18. #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
  19. #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
  20. #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͸
  21. #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
  22. #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