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
NLP2021 WS2 AI王 〜クイズAI日本一決定戦〜 報告スライド
Search
junya-takayama
March 19, 2021
Research
0
1k
NLP2021 WS2 AI王 〜クイズAI日本一決定戦〜 報告スライド
言語処理学会第27回年次大会ワークショップ2「AI王 〜クイズAI日本一決定戦〜」
での報告資料です
junya-takayama
March 19, 2021
Tweet
Share
More Decks by junya-takayama
See All by junya-takayama
[SNLP2021] Prefix-Tuning: Optimizing Continuous Prompts for Generation
tkym1220
0
600
Other Decks in Research
See All in Research
[RSJ25] Enhancing VLA Performance in Understanding and Executing Free-form Instructions via Visual Prompt-based Paraphrasing
keio_smilab
PRO
0
110
A scalable, annual aboveground biomass product for monitoring carbon impacts of ecosystem restoration projects
satai
4
230
在庫管理のための機械学習と最適化の融合
mickey_kubo
3
1.1k
SNLP2025:Can Language Models Reason about Individualistic Human Values and Preferences?
yukizenimoto
0
120
Adaptive Experimental Design for Efficient Average Treatment Effect Estimation and Treatment Choice
masakat0
0
160
ストレス計測方法の確立に向けたマルチモーダルデータの活用
yurikomium
0
1.5k
Delta Airlines® Customer Care in the U.S.: How to Reach Them Now
bookingcomcustomersupportusa
0
110
CVPR2025論文紹介:Unboxed
murakawatakuya
0
150
20250725-bet-ai-day
cipepser
2
420
Generative Models 2025
takahashihiroshi
25
13k
多言語カスタマーインタビューの“壁”を越える~PMと生成AIの共創~ 株式会社ジグザグ 松野 亘
watarumatsuno
0
120
VectorLLM: Human-like Extraction of Structured Building Contours via Multimodal LLMs
satai
4
200
Featured
See All Featured
YesSQL, Process and Tooling at Scale
rocio
173
14k
Scaling GitHub
holman
463
140k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
358
30k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
Faster Mobile Websites
deanohume
309
31k
RailsConf 2023
tenderlove
30
1.2k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.9k
Fireside Chat
paigeccino
39
3.6k
Building Flexible Design Systems
yeseniaperezcruz
328
39k
Building a Modern Day E-commerce SEO Strategy
aleyda
43
7.6k
Git: the NoSQL Database
bkeepers
PRO
431
66k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
15
1.6k
Transcript
NLP2021 WS2 AIԦ ʙΫΠζAIຊҰܾఆઓʙ େൃදձ γεςϜใࠂ ͓ؾ࣋ͪղઆ 2021/03/19 େࡕେֶେֶӃใՊֶݚڀՊ ߴࢁ
൏
ࣗݾհ Ø໊લ ߴࢁ ൏ Øॴଐ େࡕେֶَ௩ݚڀࣨ % Ø5XJUUFS!ULZN Ø63-IUUQTKVOZBUBLBZBNBHJUIVCJP
ØීஈͷݚڀτϐοΫ ରγεςϜɾࣗવݴޠੜ ØࢀՃͷ͖͔͚ͬ • ࠷ۙΫΠζʹϋϚ͍ͬͯΔ͔Β • ίϯϖͱ͍͏ͷʹग़ͯΈ͔͔ͨͬͨΒ ઈࢍब׆தͰ͢ʂʂ 1
େํ • ϦʔμʔϘʔυΛҙਂ͘؍ͨ݁͠ՌͳΜ͔օͦ͏ͯͨ͠ͷͰ #&35ͱγϯϓϧͳ *3ख๏ͷΞϯαϯϒϧΛ࠾༻ ʢ·͋ײతʹදϕʔεͰdׂղ͚ͦ͏ͳײ͕͢͡Δʣ • ܭࢉࢿݯతʹ #&35ຊདྷͷઃఆతʹೖྗΛ/τʔΫϯʹ͑Δඞཁ͋Γ •
ઌ಄/τʔΫϯͱ͔Ͱͬͯɼղʹඞཁͳ͕ࣝͪΌΜͱೖΔͷ͔ʁ ʢആ༏ͷهࣄͱ͔ɼग़ԋ࡞ΘΓͱޙΖͷํʹॻ͍ͯ͋ΔΑͶʣ • ඞཁͳؚ͕ࣝ·ΕΔΑ͏ʹͪΐͬͱݡ͍ΓํΛ͍ͨ͠ 2
ઌ಄/τʔΫϯͰ͑ΒΕͳͦ͞͏ͳྫ ଉࢠʹആ༏ͷେɺ່ʹঁ༏ͷҍΛ࣋ͭɺʰϥεταϜϥΠʱ ͳͲͷөըͰ͓ͳ͡Έͷຊͷആ༏ͱ͍͑୭Ͱ͠ΐ͏ʁ ਖ਼ղهࣄɿลݠ ˠ ΫΤϦʹԠͯ͡͏·͘هࣄຊจΛཁ͍ͨ͠ʜʜ 3 ʮଉࢠʹആ༏ͷେɺ່ʹঁ༏ͷҍʯʹؔ͢Δॳग़ ʮϥεταϜϥΠʯॳग़ ઌ಄τʔΫϯʢ͍͍ͩͨʣ
ˣ·ͩ·ͩଓ͘
#&35ϕʔεछͱ *3ϕʔεछͷΞϯαϯϒϧʢॏΈ͖ͭฏۉʣ ೖྗσʔλʢڞ௨ʣ γεςϜશମ૾ 4 BERT for ཁ BERT for
લ IR (TF-IDF) *3 $IBSOHSBN จ ީิهࣄू߹ ཁث ॏ Έ ͭ ͖ ฏ ۉ ༧ଌهࣄ BSHNBY
ཁث ϞνϕʔγϣϯจதͷϑϨʔζΛଟؚ͘ΉΑ͏ʹهࣄΛཁ͍ͨ͠ ˠީิهࣄ ! ͷຊจத͔Βɼจ " தͷ୯ޠΛଟ͘ඃ෴͢ΔΑ͏ʹ จΛෳநग़͠ɼ૯୯ޠ # ҎԼͷཁจॻ
̃ ! Λ࡞͢Δ తؔɿ% = '( ∩ ' ̃ * '( ʢͨͩ͠ '( จதͷ୯ޠू߹ɼ' ̃ * ཁจॻதͷ୯ޠू߹ʣ % ྼϞδϡϥੑΛ࣋ͭͨΊɼ্࣮ % ͕࠷େ͖͘ͳΔจΛஞ࣍తʹ ̃ ! ʹՃ͍͑ͯ͘ΞϓϩʔνΛͱΔʢᩦཉ๏ʣ 5
ཁثͷग़ྗྫ จ ଉࢠʹആ༏ͷେɺ່ʹঁ༏ͷҍΛ࣋ͭɺʰϥεταϜϥΠʱͳͲ ͷөըͰ͓ͳ͡Έͷຊͷആ༏ͱ͍͑୭Ͱ͠ΐ͏ʁ ਖ਼ղهࣄʢลݠʣݪจลݠʢΘͨͳ͚Μɺ݄ʣɺຊͷആ༏ɻຊ໊ಉ͡ɻ৽ ׁݝڕপ܊ਆଜʢݱɿڕপࢢʣग़ɻԋܶूஂԁΛܦ͔ͯΒέΠμογϡॴଐɻੈք֤ࠃʹ͓͍ͯөըΛத ৺ʹςϨϏυϥϚɺɺςϨϏίϚʔγϟϧͱ෯͘׆༂͍ͯ͠ΔຊΛද͢Δആ༏ͷҰਓɻDNɺମॏ LHɻͷล྄ҰըՈͱͯ͠׆ಈ͍ͯ͠Δɻ৽ׁݝڕপ܊ਆଜʹͯڞʹڭࢣΛ͍ͯͨ྆͠ͷݩʹੜ·ΕΔɻ ྆ͷసۈͰ༮গظΛೖଜɺकଜʢͱʹڕপࢢʣɺߴాࢢʢ্ӽࢢʣͰա͢͝ɻʜʜʢதུʣʜʜҰ༂શࠃతͳ ਓؾΛ֫ಘɺελʔμϜʹͷ্͕͠Δɻ·ͨɺͦͷࠒ͔ΒՎखͱͯ͠ࠒ·Ͱ׆ಈ͍ͯͨ͠ɻҎ߱ɺɾςϨ
ϏυϥϚͳͲͰ࣍ʑͱେΛԋ͡ɺલ్༸ʑʹݟ͑ͨɺөըॳओԋͱͳΔͣͰ͋ͬͨʰఱͱʢ୯ޠʣ ਖ਼ղهࣄʢลݠʣཁ ลݠʢΘͨͳ͚Μɺ݄ʣɺຊͷആ༏ɻຊ໊ಉ͡ɻ৽ ׁݝڕপ܊ਆଜʢݱɿڕপࢢʣग़ɻຊࠃ֎өըॳग़ԋͱͳͬͨΞϝϦΧөըʰϥεταϜϥΠʱ ʢެ։ʣͰɺลಉͷୈճΞΧσϛʔॿԋஉ༏ͳΒͼʹୈճΰʔϧσϯάϩʔϒॿԋஉ༏ɺ ୈճαλʔϯॿԋஉ༏ʹϊϛωʔτ͞ΕΔߴ͍ධՁΛಘΔɻ·ͨɺөըެ։ͱಉ࣌͡ظʹൃදͨࣗ͠Βͷஶॻ ʰ୭ 8)0".* ʱͰɺ͔ͭͯന݂පͷ࣏ྍதසൟʹड͚ͨ༌݂ʢओʹ݂খ൘༌݂ʣ͕ݪҼͰ$ܕ؊ԌΠϧεʹײછ͠ɺ ʰ໌ͷهԱʱͷࡱӨͦͷ࣏ྍͷ෭࡞༻ʹ·͞Εͳ͕Βߦ͍ͯͨ͜͠ͱΛࠂനɻ࣌Λಉͯ͘͡͠ςϨϏ౦ژͷαε ϖϯευϥϚͷڞԋΛػʹΓ߹ͬͨঁ༏ͷೆՌาͱຊ֨తʹަࡍΛ։࢝͠ɺಉ݄ʹ࠶ࠗɻͳ͓ɺଉࢠͷେ ͱؒతʹͰ͋Δ͕ڞԋྺ͋Δ͕ɺ່ͷҍͱऀۀҎ֎Ͱڞԋͨ͜͠ͱͳ͍ɻ 6
#&35ϕʔεྨث ͋Δબࢶ͕ਖ਼ղ͔Ͳ͏͔ఆ͢Δࡍʹଞͷબࢶߟྀ͍ͤͨ͞ ˠ #&35 4FMG"UUFOUJPO-BZFSͷ֊ܕΞʔΩςΫνϟΛ࠾༻ 7 ࠷ऴ <$-4> ࠷ऴ .BY1PPMJOH
<$-4>จ<4&1>هࣄ<4&1> <$-4>จ<4&1>هࣄ<4&1> ʜ ʜ BERT BERT BERT Self Attention Layer Softmax Linear Linear Linear
*3Ϟσϧ <5'*%'ϕʔε> • จͷ 5'*%'ϕΫτϧͱީิهࣄͷ 5'*%'ϕΫτϧͷ DPTྨࣅ͕ߴ͍هࣄΛਖ਼ղީิͱ͢ΔγϯϓϧͳϞσϧ • ͨͩ͠ *%'ʢίʔύεશମͰͳ͘ʣ֤͝ͱʹ
ͦͷͷީิهࣄશମʢ݅ʣ͔Βܭࢉ <ཧ༝>ީิهࣄू߹ͦͦʢ8JLJQFEJB7FDతʹʣྨࣅ͓ͯ͠Γɼ ίʔύεશମ͔Βܭࢉͨ͠ *%'Λ༻͍Δͱ 5'*%'ϕΫτϧ͕௵Εͦ͏ ʢͳؾ͕͢Δʂʂʣʢະݕূʣ <$IBSBDUFS/HSBNϕʔε> • จͷ /HSBNू߹ͱީิهࣄͷ /HSBNू߹ͷ 4JNQTPO • ୯ޠΑΓจࣈ /HSBNͷํ͕ "DDVSBDZ͕͘Β͍ߴ͔ͬͨ 8
ͦͷଞࡉʑͱͨ͠ʢCVUΫϦςΟΧϧͳʣલॲཧ • <*3 $IBS >ίʔύεதͷස্Ґޠͷ͏ͪʮετοϓϫʔυͳʔʯͱ ࢥͬͨͷΛετοϓϫʔυϦετʹՃɽείΞܭࢉ࣌ʹআ֎ • <*3 ྆ํ >ΤϯςΟςΟ໊͕จதʹؚ·Ε͍ͯͨΒਖ਼ղީิ͔Βআ
ʢʮIPHF GVHB ͱ͋ͱԿͰ͠ΐ͏ʁʯͰ IPHF GVHB ͕બΕ͕ͪ ͩͬͨͨΊʣ • <ཁث>ετοϓϫʔυతؔ ! ͷܭࢉ࣌ʹߟྀ͠ͳ͍ • <ཁث>ɻͰจׂ͢Δ͕ɼ͗͢Δ߹ʢʣ૭෯Λ ୯ޠ ͱͯ͠ɼ૭Λٖࣅతͳจͱ͢Δ • <ཁث>લจ࠷ॳ͔ΒཁจʹՃ 9
%FWͰͷ࣮ݧ݁Ռ <ओཁͳ࣮ݧઃఆ> • #&35Ϟσϧͷ࠷େτʔΫϯɿʢϞσϧڞ௨ʣ • #&35ࣄલֶशࡁΈϞσϧɿcl-tohoku/bert-base-japanese-whole-word-masking • *3 $IBSBDUFS/HSBN ͷ
A/A • ܇࿅σʔλɿ5SBJOͷΈɽΞϯαϯϒϧͷॏΈ %FWͰௐ <࣮ݧ݁Ռ> 10 Ϟσϧ "DDVSBDZ<> %FW %FW *3 5'*%' 64.72 61.79 *3 $IBSCJHSBN 72.66 69.71 *3 $IBSUSJHSBN 74.77 73.82 #&35 લτʔΫϯ 84.62 83.55 #&35 ཁ 88.94 89.67 Ξϯαϯϒϧ 92.05 91.14
ϦʔμʔϘʔυ "DDॱҐҐλΠʢ࣌ʣ Ґ ʢ࣌ʣ ʢʮ·͋ҐҎʹΔΖʯͱ͔ࢥͬͯͨͷʹʜʜʣ 11
ॴײ <ল> • ʮͰ͕͢ʯͷʮͰ͕͢ʯલ෦ͱ͔ฒྻͷྻڍ෦ͱ͔ɼ هࣄݕࡧʹ͍Βͳͦ͏ͳ෦Λؤுͬͯআڈͯ͠ΈΔ͖͔ͩͬͨ • จͱީิهࣄͷؒʹ͏ ϗοϓ͘Β͍ඞཁͦ͏ͳ͕݁ߏ͕͋ͬͨɼ ݟͯݟ͵ৼΓΛͯ͠͠·ͬͨ <ײ>
• ࠷ۙ #&35 #"35ʹͱʹ͔͘ͳΜͰಥͬࠐΉ͜ͱ͕ଟ͔ͬͨͷͰɼ ٱʑʹࣗવݴޠॲཧಓͰటष͍લॲཧΛΕָ͔ͯͬͨ͠Ͱ͢ • ίϯϖָ͍͠Ͱ͢Ͷɽ,BHHMFͱ͔ͬͯΈΑ͏ͱࢥ͍·ͨ͠ ओ࠵ऀͷօ༷ɼָ͍͠ίϯϖΛاըͯͩ͘͠͞Γ͋Γ͕ͱ͏͍͟͝·ͨ͠ʂʂʂ ઈࢍब׆தͰ͢ʂʂ 12