Scott Wen en-tau au Yih
Who is Justin Bieberβs sister? Jazmyn Bieber semantic parsing Knowledge ππ¦. sister_of(justin_bieber, π¦) Base query matching ππ¦. sibling_of(justin_bieber, x ) β§ gender( x , female)
Who is Justin Bieberβs sister? Jazmyn Bieber Knowledge semantic parsing Base query ππ¦. sibling_of(justin_bieber, x ) β§ gender( x , female)
βWhat was the date that Minnesota became a state?β βWhen was the state Minnesota created?β βMinnesota's date it entered the union?β location.dated_location.date_founded
Basic idea directly grows staged
Addresses Key Challenges 52.5
β’ Introduction β’ Background β’ Graph knowledge base β’ Query graph
12/26/1999 β’ from Mila Kunis β’ cvt1 Meg Griffin β’ Family Guy Lacey Chabert cvt2 series cvt3 1/31/1999
constraints Meg Griffin argmin topic entity core inferential chain Family Guy cast y x
β’ Introduction β’ Background β’ Staged Query Graph Generation (Our Approach) β’ Link topic entity β’ Identify core inferential chain β’ Augment constraints
Staged Meg Family Guy (1) Link Topic Entity s 1 Family Guy s 0 Ο s 2 Meg Griffin
Staged Meg Family Guy (2) Identify Core Inferential Chain s 3 Family Guy cast actor y x s 1 s 4 Family Guy Family Guy writer start y x s 5 Family Guy genre x
Staged Meg Family Guy (3) Augment Constraints s 3 Family Guy cast actor y x s 6 Meg Griffin Family Guy cast actor y x s 7 argmin Meg Griffin Family Guy y x
s 1 Family Guy s 0 Ο s 2 Meg Griffin
s 3 Family Guy cast actor y x s 1 s 4 Family Guy Family Guy writer start y x s 5 Family Guy genre x Who first voiced Meg on Family Guy? { castβactor, writerβstart, genre }
β’ Input is mapped to two π -dimensional vectors 300 exp cos(π§ π , π§ π ) π π π = π β² exp cos(π§ π β² , π§ π ) 300 ... π§ π β R π π§ π β R π ... max max max ... ... ... ... 1000 1000 1000 ... 15K 15K 15K 15K 15K castβactor who voiced meg on π <s> w 1 w 2 w T </s>
s 3 Family Guy cast actor y x s 6 Meg Griffin β’ Who voiced Family Guy Family Guy cast actor y x s 7 argmin Meg Griffin s 3 Family Guy cast actor Family Guy y x y x cast FamilyGuy π§ actor π§ π¦ β’ One or more constraint nodes can be added to π§ or π¦ β’ π§ : Additional property of this event (e.g., character π§ MegGriffin ) β’ π¦ : Additional property of the answer entity (e.g., gender)
Who first voiced Meg on Family Guy? s 3 Family Guy cast actor y x s 4 Family Guy writer start y x
Who first voiced Meg on Family Guy? s 7 argmin Meg Griffin Family Guy y x s 3 Family Guy cast actor y x
π = Who first voiced Meg on Family Guy? Meg Griffin argmin π‘ = Family Guy cast y x
β’ Introduction β’ Background β’ Staged Query Graph Generation (Our Approach) β’ Experiments β’ Data & evaluation metric β’ Creating training data from Q/A pairs β’ Results
β’ What character did Natalie Portman play in Star Wars? Padme Amidala β’ What currency do you use in Costa Rica? Costa Rican colon β’ What did Obama study in school? political science β’ What do Michelle Obama do for a living? writer, lawyer β’ 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 πΏ
Avg. F1 (Accuracy) on WebQuestions Test Set 60 52.5 50 45.3 44.3 41.3 39.9 39.2 40 37.5 35.7 33 30 20 10 0 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
Recommend
More recommend