SlideShare una empresa de Scribd logo
1 de 32
Descargar para leer sin conexión
Scott Wen-tau Yih
Knowledge
Base
𝜆𝑥. sister_of(justin_bieber, 𝑥)
Who is Justin Bieber’s sister?
𝜆𝑥. sibling_of(justin_bieber, x) ∧ gender(x, female)
semantic parsing
query
matching
Jazmyn Bieber
Knowledge
Base
Who is Justin Bieber’s sister?
𝜆𝑥. sibling_of(justin_bieber, x) ∧ gender(x, female)
semantic parsing
query
Jazmyn Bieber
“What was the date that Minnesota became a state?”
“When was the state Minnesota created?”
“Minnesota's date it entered the union?”
location.dated_location.date_founded
directly
grows staged
Basic idea
Addresses Key Challenges
52.5
• Introduction
• Background
• Graph knowledge base
• Query graph
•
•
• Family Guy cvt2
Meg Griffin
Lacey Chabert
1/31/1999
cvt1
from
12/26/1999
cvt3
series
Mila Kunis
Family Guy cast
Meg Griffinargmin
xy
topic entity core inferential chain
constraints
• Introduction
• Background
• Staged Query Graph Generation (Our Approach)
• Link topic entity
• Identify core inferential chain
• Augment constraints
Staged
Meg Family Guy
Family Guy
s1
Meg Griffin
s2
ϕ
s0
(1) Link Topic Entity
Staged
Meg Family Guy
(2) Identify Core Inferential Chain
Family Guy
s1
Family Guy cast actor xy
s3
Family Guy writer start xy
s4
Family Guy genre x
s5
Staged
Meg Family Guy
(3) Augment Constraints
Family Guy cast actor xy
Family Guy cast actor xy
Meg Griffin
Family Guy xy
Meg Griffinargmin
s3
s6
s7
Family Guy
s1
Meg Griffin
s2
ϕ
s0
Family Guy
s1
Family Guy cast actor xy
s3
Family Guy writer start xy
s4
Family Guy genre x
s5
Who first voiced Meg on Family Guy?
{cast−actor, writer−start, genre}
• Input is mapped to two 𝑘-dimensional vectors
𝑃 𝑅 𝑃 =
exp cos(𝑦 𝑅, 𝑦 𝑃)
𝑅′ exp cos(𝑦 𝑅′, 𝑦 𝑃)
𝑦 𝑃 ∈ R 𝑘 𝑦 𝑅 ∈ R 𝑘
who voiced meg on 𝑒 cast−actor
15K 15K 15K 15K 15K
1000 1000 1000
max max
...
...
... max
300
...
...
<s> w1 w2 wT </s>
... ...
300
• Who voiced Family Guy
cast FamilyGuy 𝑦 actor 𝑦 𝑥
• One or more constraint nodes can be added to 𝑦 or 𝑥
• 𝑦 : Additional property of this event (e.g., character 𝑦 MegGriffin )
• 𝑥 : Additional property of the answer entity (e.g., gender)
Family Guy cast actor xy
Family Guy cast actor xy
Meg Griffin
Family Guy xy
Meg Griffinargmin
s3
s6
s7
Family Guy cast actor xy
s3
Who first voiced Meg on Family Guy?
Family Guy cast actor xy
s3
Family Guy writer start xy
s4
Who first voiced Meg on Family Guy?
Family Guy cast actor xy
s3
Family Guy xy
Meg Griffinargmin
s7
𝑞 =Who first voiced Meg on Family Guy?
Family Guy cast
Meg Griffinargmin
xy
𝑠 =
• Introduction
• Background
• Staged Query Graph Generation (Our Approach)
• Experiments
• Data & evaluation metric
• Creating training data from Q/A pairs
• Results
• What character did Natalie Portman play in Star Wars? Padme Amidala
• What currency do you use in Costa Rica? Costa Rican colon
• What did Obama study in school? political science
• What do Michelle Obama do for a living? writer, lawyer
• What killed Sammy Davis Jr? throat cancer [Examples from Berant]
Relation Matching (Identifying Core Inferential Chain)
Pattern Inferential Chain
what was <e> known for people.person.profession
what kind of government does <e> have location.country.form_of_government
what year were the <e> established sports.sports_team.founded
what city was <e> born in people.person.place_of_birth
what did <e> die from people.deceased_person.cause_of_death
who married <e> people.person.spouse_s
people.marriage.spouse
Reward Function 𝛾
33
35.7
37.5
39.2 39.9 41.3
44.3 45.3
52.5
0
10
20
30
40
50
60
Avg. F1 (Accuracy) on WebQuestions Test Set
Yao-14 Berant-13 Bao-14 Bordes-14b Berant-14 Yang-14 Yao-15 Wang-14 Yih-15
Method #Entities Covered Ques. Labeled Ent.
Freebase API 19,485 98.8% 81.2%
Yang & Chang, ACL-15 9,147 99.8% 87.8%
52.5% 48.4%
49.6 52.5
A random sample of 100 incorrectly answered questions
directly
http://aka.ms/sent2vec
http://aka.ms/codalab-webq
http://aka.ms/stagg

Más contenido relacionado

Más de Association for Computational Linguistics

Más de Association for Computational Linguistics (20)

Daniel Gildea - 2018 - The ACL Anthology: Current State and Future Directions
Daniel Gildea - 2018 - The ACL Anthology: Current State and Future DirectionsDaniel Gildea - 2018 - The ACL Anthology: Current State and Future Directions
Daniel Gildea - 2018 - The ACL Anthology: Current State and Future Directions
 
Wenqiang Lei - 2018 - Sequicity: Simplifying Task-oriented Dialogue Systems w...
Wenqiang Lei - 2018 - Sequicity: Simplifying Task-oriented Dialogue Systems w...Wenqiang Lei - 2018 - Sequicity: Simplifying Task-oriented Dialogue Systems w...
Wenqiang Lei - 2018 - Sequicity: Simplifying Task-oriented Dialogue Systems w...
 
Matthew Marge - 2017 - Exploring Variation of Natural Human Commands to a Rob...
Matthew Marge - 2017 - Exploring Variation of Natural Human Commands to a Rob...Matthew Marge - 2017 - Exploring Variation of Natural Human Commands to a Rob...
Matthew Marge - 2017 - Exploring Variation of Natural Human Commands to a Rob...
 
Venkatesh Duppada - 2017 - SeerNet at EmoInt-2017: Tweet Emotion Intensity Es...
Venkatesh Duppada - 2017 - SeerNet at EmoInt-2017: Tweet Emotion Intensity Es...Venkatesh Duppada - 2017 - SeerNet at EmoInt-2017: Tweet Emotion Intensity Es...
Venkatesh Duppada - 2017 - SeerNet at EmoInt-2017: Tweet Emotion Intensity Es...
 
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 WorkshopSatoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
 
Chenchen Ding - 2015 - NICT at WAT 2015
Chenchen Ding - 2015 - NICT at WAT 2015Chenchen Ding - 2015 - NICT at WAT 2015
Chenchen Ding - 2015 - NICT at WAT 2015
 
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
 
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
John Richardson - 2015 - KyotoEBMT System Description for the 2nd Workshop on...
 
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
 
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
Zhongyuan Zhu - 2015 - Evaluating Neural Machine Translation in English-Japan...
 
Hyoung-Gyu Lee - 2015 - NAVER Machine Translation System for WAT 2015
Hyoung-Gyu Lee - 2015 - NAVER Machine Translation System for WAT 2015Hyoung-Gyu Lee - 2015 - NAVER Machine Translation System for WAT 2015
Hyoung-Gyu Lee - 2015 - NAVER Machine Translation System for WAT 2015
 
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 WorkshopSatoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
Satoshi Sonoh - 2015 - Toshiba MT System Description for the WAT2015 Workshop
 
Chenchen Ding - 2015 - NICT at WAT 2015
Chenchen Ding - 2015 - NICT at WAT 2015Chenchen Ding - 2015 - NICT at WAT 2015
Chenchen Ding - 2015 - NICT at WAT 2015
 
Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...
Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...
Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...
 
Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...
Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...
Graham Neubig - 2015 - Neural Reranking Improves Subjective Quality of Machin...
 
Terumasa Ehara - 2015 - System Combination of RBMT plus SPE and Preordering p...
Terumasa Ehara - 2015 - System Combination of RBMT plus SPE and Preordering p...Terumasa Ehara - 2015 - System Combination of RBMT plus SPE and Preordering p...
Terumasa Ehara - 2015 - System Combination of RBMT plus SPE and Preordering p...
 
Terumasa Ehara - 2015 - System Combination of RBMT plus SPE and Preordering p...
Terumasa Ehara - 2015 - System Combination of RBMT plus SPE and Preordering p...Terumasa Ehara - 2015 - System Combination of RBMT plus SPE and Preordering p...
Terumasa Ehara - 2015 - System Combination of RBMT plus SPE and Preordering p...
 
Toshiaki Nakazawa - 2015 - Overview of the 2nd Workshop on Asian Translation
Toshiaki Nakazawa  - 2015 - Overview of the 2nd Workshop on Asian TranslationToshiaki Nakazawa  - 2015 - Overview of the 2nd Workshop on Asian Translation
Toshiaki Nakazawa - 2015 - Overview of the 2nd Workshop on Asian Translation
 
Hua Shan - 2015 - A Dependency-to-String Model for Chinese-Japanese SMT System
Hua Shan - 2015 - A Dependency-to-String Model for Chinese-Japanese SMT SystemHua Shan - 2015 - A Dependency-to-String Model for Chinese-Japanese SMT System
Hua Shan - 2015 - A Dependency-to-String Model for Chinese-Japanese SMT System
 
Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...
Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...
Wei Yang - 2015 - Sampling-based Alignment and Hierarchical Sub-sentential Al...
 

Último

Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
negromaestrong
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
PECB
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
Chris Hunter
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
kauryashika82
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
QucHHunhnh
 

Último (20)

Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
Mattingly "AI & Prompt Design: Structured Data, Assistants, & RAG"
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric  nursing HISTORY  COLLECTION  .docxpsychiatric  nursing HISTORY  COLLECTION  .docx
psychiatric nursing HISTORY COLLECTION .docx
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
Explore beautiful and ugly buildings. Mathematics helps us create beautiful d...
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
 
Advance Mobile Application Development class 07
Advance Mobile Application Development class 07Advance Mobile Application Development class 07
Advance Mobile Application Development class 07
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writing
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi  6.pdf1029-Danh muc Sach Giao Khoa khoi  6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Class 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdfClass 11th Physics NEET formula sheet pdf
Class 11th Physics NEET formula sheet pdf
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 

Scott Wen-tau Yih - 2015 - Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base

  • 2.
  • 3.
  • 4. Knowledge Base 𝜆𝑥. sister_of(justin_bieber, 𝑥) Who is Justin Bieber’s sister? 𝜆𝑥. sibling_of(justin_bieber, x) ∧ gender(x, female) semantic parsing query matching Jazmyn Bieber
  • 5. Knowledge Base Who is Justin Bieber’s sister? 𝜆𝑥. sibling_of(justin_bieber, x) ∧ gender(x, female) semantic parsing query Jazmyn Bieber
  • 6. “What was the date that Minnesota became a state?” “When was the state Minnesota created?” “Minnesota's date it entered the union?” location.dated_location.date_founded
  • 9. • Introduction • Background • Graph knowledge base • Query graph
  • 10. • • • Family Guy cvt2 Meg Griffin Lacey Chabert 1/31/1999 cvt1 from 12/26/1999 cvt3 series Mila Kunis
  • 11. Family Guy cast Meg Griffinargmin xy topic entity core inferential chain constraints
  • 12. • Introduction • Background • Staged Query Graph Generation (Our Approach) • Link topic entity • Identify core inferential chain • Augment constraints
  • 13. Staged Meg Family Guy Family Guy s1 Meg Griffin s2 ϕ s0 (1) Link Topic Entity
  • 14. Staged Meg Family Guy (2) Identify Core Inferential Chain Family Guy s1 Family Guy cast actor xy s3 Family Guy writer start xy s4 Family Guy genre x s5
  • 15. Staged Meg Family Guy (3) Augment Constraints Family Guy cast actor xy Family Guy cast actor xy Meg Griffin Family Guy xy Meg Griffinargmin s3 s6 s7
  • 17. Family Guy s1 Family Guy cast actor xy s3 Family Guy writer start xy s4 Family Guy genre x s5 Who first voiced Meg on Family Guy? {cast−actor, writer−start, genre}
  • 18. • Input is mapped to two 𝑘-dimensional vectors 𝑃 𝑅 𝑃 = exp cos(𝑦 𝑅, 𝑦 𝑃) 𝑅′ exp cos(𝑦 𝑅′, 𝑦 𝑃) 𝑦 𝑃 ∈ R 𝑘 𝑦 𝑅 ∈ R 𝑘 who voiced meg on 𝑒 cast−actor 15K 15K 15K 15K 15K 1000 1000 1000 max max ... ... ... max 300 ... ... <s> w1 w2 wT </s> ... ... 300
  • 19. • Who voiced Family Guy cast FamilyGuy 𝑦 actor 𝑦 𝑥 • One or more constraint nodes can be added to 𝑦 or 𝑥 • 𝑦 : Additional property of this event (e.g., character 𝑦 MegGriffin ) • 𝑥 : Additional property of the answer entity (e.g., gender) Family Guy cast actor xy Family Guy cast actor xy Meg Griffin Family Guy xy Meg Griffinargmin s3 s6 s7 Family Guy cast actor xy s3
  • 20. Who first voiced Meg on Family Guy? Family Guy cast actor xy s3 Family Guy writer start xy s4
  • 21. Who first voiced Meg on Family Guy? Family Guy cast actor xy s3 Family Guy xy Meg Griffinargmin s7
  • 22. 𝑞 =Who first voiced Meg on Family Guy? Family Guy cast Meg Griffinargmin xy 𝑠 =
  • 23. • Introduction • Background • Staged Query Graph Generation (Our Approach) • Experiments • Data & evaluation metric • Creating training data from Q/A pairs • Results
  • 24. • What character did Natalie Portman play in Star Wars? Padme Amidala • What currency do you use in Costa Rica? Costa Rican colon • What did Obama study in school? political science • What do Michelle Obama do for a living? writer, lawyer • What killed Sammy Davis Jr? throat cancer [Examples from Berant]
  • 25. Relation Matching (Identifying Core Inferential Chain) Pattern Inferential Chain what was <e> known for people.person.profession what kind of government does <e> have location.country.form_of_government what year were the <e> established sports.sports_team.founded what city was <e> born in people.person.place_of_birth what did <e> die from people.deceased_person.cause_of_death who married <e> people.person.spouse_s people.marriage.spouse
  • 27. 33 35.7 37.5 39.2 39.9 41.3 44.3 45.3 52.5 0 10 20 30 40 50 60 Avg. F1 (Accuracy) on WebQuestions Test Set Yao-14 Berant-13 Bao-14 Bordes-14b Berant-14 Yang-14 Yao-15 Wang-14 Yih-15
  • 28. Method #Entities Covered Ques. Labeled Ent. Freebase API 19,485 98.8% 81.2% Yang & Chang, ACL-15 9,147 99.8% 87.8% 52.5% 48.4%
  • 30. A random sample of 100 incorrectly answered questions