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
【輪講資料】Zero-shot Cross-lingual Semantic Parsing
Search
Yano
May 03, 2023
0
91
【輪講資料】Zero-shot Cross-lingual Semantic Parsing
研究室内の輪講で使った資料です。
Yano
May 03, 2023
Tweet
Share
More Decks by Yano
See All by Yano
【輪講資料】ReAct: Synergizing Reasoning and Acting in Language Models / Tree of Thoughts: Deliberate Problem Solving with Large Language Models
yano0
0
110
【輪講資料】SIMLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
yano0
2
260
【輪講資料】From Zero to Hero: On the Limitations of Zero-Shot Language Transfer with Multilingual Transformers
yano0
0
65
Featured
See All Featured
Intergalactic Javascript Robots from Outer Space
tanoku
270
27k
Faster Mobile Websites
deanohume
306
31k
jQuery: Nuts, Bolts and Bling
dougneiner
63
7.7k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
114
50k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
49
2.3k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
46
2.3k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.2k
Building a Modern Day E-commerce SEO Strategy
aleyda
38
7.1k
Gamification - CAS2011
davidbonilla
80
5.2k
Scaling GitHub
holman
459
140k
Unsuck your backbone
ammeep
669
57k
Being A Developer After 40
akosma
89
590k
Transcript
Zero-shot Cross-lingual Semantic Parsing Tom Sherborne, Mirella Lapata ACL 2022
֓ཁ 2 ✓ θϩγϣοτଟݴޠҙຯղੳϞσϧɺZX-parseͷఏҊ • ݴޠؒજࡏදݱͷΞϥΠϝϯτʹண͠సҠֶशͷޡࠩΛ࠷খԽ • ෳͷଛࣦؔΛಋೖ͢ΔϚϧνλεΫֶशʹΑΓҟͳΔݴޠͷ જࡏදݱ͕ྨࣅ͢ΔΑ͏ʹ •
ରݴޠͷϖΞσʔλΛඞཁͱͤͣɺӳޠϖΞͱରݴޠͷࣗવ จͷΈར༻ ✓ θϩγϣοτҙຯղੳλεΫʹ͓͍ͯෳͷݴޠͰߴ͍ੑೳ
બΜͩཧ༝ • ݴޠԣஅతͳݚڀʹڵຯ͕͋ΔͨΊ • ಛʹݴޠԣஅతͳજࡏۭؒΛ࡞ΔͰ໘നͦ͏ • ࣗͷݚڀΛؚΉ͞·͟·ͳసҠֶशλεΫͰར༻Ͱ͖ͦ͏ 3
ҙຯղੳ (Semantic Parsing) • ࣗવݴޠͷൃΛཧܗࣜ(Logical Form)ʹม • ͞·͟·ͳλεΫͰॏཁͳΠϯϑϥ • ࣭ԠɺରγεςϜɺػցͷࢦࣔ…
4 -JTU fl JHIUTGSPN4BO'SBODJTDPUP1JUUTCVSHI 4&-&$5%*45*/$5 fl JHIU@ fl JHIU@JE'30.ʜ
• ෳͷݴޠ͔ΒͳΔࣗવจΛಉ͡ཧܗࣜʹม[1] ଟݴޠҙຯղੳ (Cross-lingual Semantic Parsing) 5 <>.VMUJMJOHVBM4FNBOUJD1BSTJOH1BSTJOH.VMUJQMF-BOHVBHFTJOUP4FNBOUJD3FQSFTFOUBUJPOT 4&-&$5%*45*/$5 fl
JHIU@ fl JHIU@JE'30.ʜ -JTU fl JHIUTGSPN4BO 'SBODJTDPUP1JUUTCVSHI αϯϑϥϯγείൃϐοπ όʔάߦ͖ͷϑϥΠτΛ ϦετΞοϓ͍ͯͩ͘͠͞ɻ ʹ
ઌߦݚڀ • ӳޠͷࣗવจ-ཧܗࣜͷฒྻσʔλΛ༁͠ɺ֤ରݴޠͷࣗવ จ-ཧܗࣜϖΞσʔλΛར༻ • ػց༁Λ༻͍Δ߹[2] • ػց༁ᘳͰͳ͍ • ಛʹϦιʔεݴޠʹ͓͍ͯ
ߴ࣭ͳػց༁͍͠ • ਓख༁Λ༻͍Δ߹[3] • ߴίετ 6 <>#PPUTUSBQQJOHB$SPTTMJOHVBM4FNBOUJD1BSTFS <>/FVSBM"SDIJUFDUVSFTGPS.VMUJMJOHVBM4FNBOUJD1BSTJOH ཧܗࣜ ӳޠ ରݴޠ ༁
• ରݴޠͷฒྻσʔλΛΘͳ͍ θϩγϣοτͱ͢Δ ➡ ӳޠͷࣗવจ-ཧܗࣜϖΞσʔλͱ ରݴޠͷࣗવจͷΈར༻ ✓ Ϟσϧߏ • ӳޠ͔Βಘͨજࡏදݱ͔Β
ཧܗࣜΛੜ͢Δσίʔμ • ݴޠԣஅతͳʢӳޠͱྨࣅͨ͠ʣ જࡏදݱΛ֫ಘ͢ΔΤϯίʔμ ఏҊख๏ 7 αϯϑϥϯγείൃϐοπ όʔάߦ͖ͷϑϥΠτΛ ϦετΞοϓ͍ͯͩ͘͠͞ɻ 4&-&$54&-&$54&-&$5 8)&3& '30.4&-&$5 Τϯίʔμ σίʔμ ❌ 4&-&$5%*45*/$5 fl JHIU@ fl JHIU@JE'30.ʜ -JTU fl JHIUTGSPN4BO 'SBODJTDPUP1JUUTCVSHI ⭕ Τϯίʔμ σίʔμ ˛ΞϥΠϝϯτΛߦΘͳ͍߹ɺݴޠ͝ͱʹ ҟͳΔજࡏදݱͱͳΓग़ྗ͕ҟͳΔ જࡏදݱ
ϚϧνλεΫֶश • ̍ͭͷΤϯίʔμʹର͠ෳͷతؔΛ༻͍ɺಉ࣌ʹ࠷దԽ[4] • ଟݴޠλεΫʹ͓͍ͯɺʮιʔεݴޠ (ӳޠͳͲ) ͰͷඪλεΫʴ ιʔεݴޠͱରݴޠͷΞϥΠϝϯτʯΛಉ࣌ʹ࠷దԽ͢Δݚڀ ͕ଘࡏ •
ԻݴޠཧղɺςΩετ؆ུԽɺґଘੑߏจղੳɺػց༁ 8 <>.VMUJUBTL4FRVFODFUP4FRVFODF-FBSOJOH
ఏҊϞσϧɿZX-Parse • ϚϧνλεΫSeq2seqϞσϧ ✓ తͷλεΫʹՃ͑ิॿతͳλεΫΛಋೖ • DLF ɿཧܗࣜͷੜ • DNL
ɿࣗવݴޠͷੜ • LPɿݴޠ༧ଌ 9 Τϯίʔμ z DLF LP ࣗવจ DNL ֶश(EN) ਪ જࡏදݱ Transformer x 6 (mBARTͷΤϯίʔμ) Transformer x 6 ֶश(ଞݴޠ) ཧܗࣜͷੜ ӳޠͰͷΈֶश
DLF ɿ Generating Logical Forms 10 Τϯίʔμ z DLF LP
List fl ights from San Francisco to Pittsburgh? DNL SELECT DISTINCT fl ight_1. fl ight_id FROM … • ӳޠͷࣗવจ͔Βಉ͡ҙຯͷཧܗࣜΛੜ͢Δ ➡ཧܗࣜੜೳྗΛʹ͚ͭΔ ֶश࣌ ਪ࣌ જࡏදݱ
• ରݴޠͷࣗવจʹϊΠζΛՃ͑ɺ࠶ߏங͘͠ӳޠ༁ ➡֤ݴޠͷࣗવจʹΤϯίʔμʔΛదԠͤ͞Δ • ݴޠݻ༗ͷಛੑΛʹ͚Δ DNL ɿ Generating Natural Language
11 Τϯίʔμ z DLF LP αϯϑϥϯγείൃϐοπ όʔάߦ͖ͷϑϥΠτΛ ϦετΞοϓ͍ͯͩ͘͠͞ɻ DNL Н ϊΠζ Н αϯϑϥϯγείൃϐοπ όʔάߦ͖ͷϑϥΠτΛ ϦετΞοϓ͍ͯͩ͘͠͞ɻ List fl ights from San Francisco to Pittsburgh? ֶश࣌ ਪ࣌ જࡏදݱ
LPɿ Language Prediction 12 Τϯίʔμ z DLF LP List fl
ights from San Francisco to Pittsburgh? DNL English ֶश࣌ ਪ࣌ • ೖྗจͷݴޠΛྨثͰ༧ଌ͢Δ ➡ΤϯίʔμʹݴޠΛ۠ผͤ͞Δ જࡏදݱ
LPɿ Language Prediction 13 Τϯίʔμ z DLF LP List fl
ights from San Francisco to Pittsburgh? DNL English ֶश࣌ ਪ࣌ • ೖྗจͷݴޠΛྨثͰ༧ଌ͢Δ ➡ΤϯίʔμʹݴޠΛ۠ผͤ͞Δ ✦ ٯ࣌ʹޯΛసͤ͞Δ ➡ ݴޠΛ۠ผͤ͞ͳ͍ • ݴޠʹͱΒΘΕͳ͍දݱ જࡏදݱ
• ಉ࣌ʹ̏ͭͷతؔΛ࠷దԽ • ཧܗࣜͷੜʴݴޠ͝ͱͷಛΛֶशʴݴޠΛ۠ผ͠ͳ͍ • ରݴޠͷϖΞίʔύεΛඞཁͱ͠ͳ͍θϩγϣοτҙຯղੳ ZX-Parse 14 Τϯίʔμ z
DLF LP DNL ٯ࣌ ཧܗࣜͷੜ ࣗવݴޠͷੜ ʢ࠶ߏ/༁ʣ ݴޠ༧ଌ − ∂LLP ∂θ ∂LNL ∂θ ∂LLF ∂θ જࡏදݱ
σʔληοτ ✦ ҙຯղੳσʔληοτ • ATIS • ཱྀߦυϝΠϯͷଟݴޠࣗવจͱཧܗࣜͷϖΞίʔύε • ӳޠ, ϑϥϯεޠ,
ϙϧτΨϧޠ, εϖΠϯޠ, υΠπޠ, தࠃޠ, ώϯσΟʔޠ, τϧίޠ • Overnight • ̔υϝΠϯͷӳޠࣗવจͱཧܗࣜͷϖΞίʔύε • ਪ࣌ͷΈ༁Ͱ࡞͞ΕͨதࠃޠͱυΠπޠσʔλΛར༻ ✦ ࣗવݴޠσʔληοτ • MKQA • ࣭จͷର༁ίʔύε • ӳޠ, ϑϥϯεޠ, ϙϧτΨϧޠ, εϖΠϯޠ, υΠπޠ, தࠃޠ • ParaCrawl • Webର༁ίʔύε 15
σʔληοτ ✦ ҙຯղੳσʔληοτ • ATIS • ཱྀߦυϝΠϯͷଟݴޠࣗવจͱཧܗࣜͷϖΞίʔύε • ӳޠ, ϑϥϯεޠ,
ϙϧτΨϧޠ, εϖΠϯޠ, υΠπޠ, தࠃޠ, ώϯσΟʔޠ, τϧίޠ • Overnight • ̔υϝΠϯͷӳޠࣗવจͱཧܗࣜͷϖΞίʔύε • ਪ࣌ͷΈ༁Ͱ࡞͞ΕͨதࠃޠͱυΠπޠσʔλΛར༻ ✦ ࣗવݴޠσʔληοτ • MKQA • ࣭จͷର༁ίʔύε • ӳޠ, ϑϥϯεޠ, ϙϧτΨϧޠ, εϖΠϯޠ, υΠπޠ, தࠃޠ • ParaCrawl • Webର༁ίʔύε 16
༁ϕʔεϥΠϯ ✦ “࠷খݶͷྗ”ϕʔεϥΠϯ • ػց༁Λ༻͍ͯ࡞ͨ͠ϕʔεϥΠϯ • Translate-Test • ςετηοτΛӳޠʹ༁ •
Translate-Train • ֶशηοτΛରݴޠʹ༁ ✦ “࠷େݶͷྗ”ϕʔεϥΠϯ • Monolingual Training • ֶशηοτΛਓखͰରݴޠʹ༁ 17
࣮ݧ݁Ռɿ༁ϕʔεϥΠϯͱͷൺֱ • ӳޠҎ֎ͷݴޠͷθϩγϣοτҙຯղੳλεΫͰSOTA 18 • Monolingual Training: ֶशηοτΛਓखͰରݴޠʹ༁ • Translate-Train:
ֶशηοτΛରݴޠʹ༁ • Translate-Test: ςετηοτΛӳޠʹ༁ • ATIS: ࣭จͱཧܗࣜͷϖΞσʔλ • Overnight: ෳυϝΠϯͷจͱཧܗࣜͷϖΞσʔλ ※ώϯσΟʔޠ(HI)ɺτϧίޠ(TR)ର༁ίʔύε͕ ଘࡏ͠ͳ͍ͨΊิॿతͰͷֶशʹؚ·Ε͍ͯͳ͍
࣮ݧ݁Ռɿ࠷খݶͷྗϕʔεϥΠϯͱͷൺֱ • ิॿతͰͷֶशΛߦͳͬͨશͯͷݴޠ(HI,TRҎ֎)ʹ͓͍ͯੑೳ্ • OvernightATIS΄Ͳੑೳ্͍ͯ͠ͳ͍ • υϝΠϯ͕ଟ༷ͳͨΊɺ՝͕ෳ߹తʹͳ͍ͬͯΔ • ӳޠʹ͍ۙݴޠͰTranslate-TrainTranslate-TestΛԼճΔ͕ɺԕ͍ݴޠ Ͱੑೳ͕Լ͢Δ
• ػց༁ͷํͷӨڹʁ 19
࣮ݧ݁ՌɿαϒλεΫͷӨڹ 20 • LFͷΈͷ߹ɺTranslate-TestΑΓੑೳ͕͍ • NLͱLPͲͪΒ͔Ճ͢Δ࣌ɺNLΛՃͨ͠ํ͕ੑೳ͕ߴ͍ • ֤ݴޠͷࣗવݴޠจʹదԠ͢Δํ͕େࣄ
࣮ݧ݁ՌɿαϒλεΫͷӨڹ 21 • LFͷΈͷ߹ɺTranslate-TestΑΓੑೳ͕͍ • NLͱLPͲͪΒ͔Ճ͢Δ࣌ɺNLΛՃͨ͠ํ͕ੑೳ͕ߴ͍ • ֤ݴޠͷࣗવจʹదԠ͢Δ͜ͱ͕େࣄ
࣮ݧ݁ՌɿαϒλεΫͷӨڹ • αϒλεΫͰֶशʹؚ·Εͳ͍ݴޠ(HI,TR)Ͱੑೳ্ • ֶश͍ͯ͠ͳͯ͘ݴޠؒͷજࡏදݱ͕վળ͞Ε͍ͯΔ 22
࣮ݧ݁ՌɿαϒλεΫͷӨڹ • αϒλεΫͰֶशʹؚ·Εͳ͍ݴޠ(HI,TR)Ͱੑೳ্ • ֶश͍ͯ͠ͳͯ͘ݴޠؒͷજࡏදݱ͕վળ͞Ε͍ͯΔ 23 ˝ຒΊࠐΈͷՄࢹԽ
࣮ݧ݁ՌɿαϒλεΫͷӨڹ • ୯ݴޠͷΈར༻͢Δ߹(τ = 0.0)ΑΓ༁ߦ͏߹(τ = 0.5) ͷੑೳ͕ߴ͍ • దͳจΛར༻͢Δ߹(ParaCrawl)ΑΓਪ࣌ͷೖྗͱಉ࣭͡
จΛֶशʹར༻͢Δ߹(MKQA)ͷੑೳ͕ߴ͍ 24
·ͱΊ ✓ θϩγϣοτଟݴޠҙຯղੳϞσϧɺZX-parseͷఏҊ • જࡏදݱͷΞϥΠϝϯτʹண͠సҠֶशͷޡࠩΛ࠷খԽ • ෳͷଛࣦؔΛಋೖ͢ΔϚϧνλεΫֶशʹΑΓҟͳΔݴޠͷ જࡏදݱ͕ྨࣅ͢ΔΑ͏ʹ • ରݴޠͷϖΞσʔλΛඞཁͱͤͣɺӳޠϖΞͱରݴޠͷࣗવ
จͷΈར༻ ✓ θϩγϣοτҙຯղੳλεΫʹ͓͍ͯෳͷݴޠͰߴ͍ੑೳ 25