SPATIO-TEMPORAL VERACITY ASSESSMENT JOANA GONZALES MALAVERRI - - PowerPoint PPT Presentation

▶
spatio temporal veracity assessment
SMART_READER_LITE
LIVE PREVIEW

SPATIO-TEMPORAL VERACITY ASSESSMENT JOANA GONZALES MALAVERRI - - PowerPoint PPT Presentation

Jan 14, 2023 402 likes •765 views

SPATIO-TEMPORAL VERACITY ASSESSMENT JOANA GONZALES MALAVERRI (LAHDAK) FATIHA SAS (LAHDAK) GIANLUCA QUERCINI (MODHEL) LABORATOIRE DE RECHERCHE EN INFORMATIQUE (LRI) {MALAVERRI, FATIHA.SAIS,GIANLUCA.QUERCINI}@LRI.FR JOURNEE ROD MOTIVATION

slide-1
SLIDE 1

SPATIO-TEMPORAL VERACITY ASSESSMENT

LABORATOIRE DE RECHERCHE EN INFORMATIQUE (LRI) {MALAVERRI, FATIHA.SAIS,GIANLUCA.QUERCINI}@LRI.FR

JOURNEE ROD

JOANA GONZALES MALAVERRI (LAHDAK) FATIHA SAÏS (LAHDAK) GIANLUCA QUERCINI (MODHEL)

slide-2
SLIDE 2

MOTIVATION

2

Extracted from https://goo.gl/B2i5aG

facts facts facts facts facts knowledge Base

slide-3
SLIDE 3

REAL-WORLD SCENARIO: WHAT IS THE BARACK OBAMA’S CITIZENSHIP

3

American

Kenyan Indonesian British

I don’t know! But the probability that all errors in the certificate were inadvertent is 1 in 75 quadrillion. https://goo.gl/ 5YTBxK

slide-4
SLIDE 4

4

Extracted from https://goo.gl/B2i5aG

facts facts facts facts facts knowledge Base

slide-5
SLIDE 5

VERACITY ASSESSMENT APPROACHES

5

  • Majority voting
  • Basic approaches
  • Extended approaches
  • Extra knowledge (ontologies)
  • Source dependency detection

[Beretta et al. 16]

slide-6
SLIDE 6

VERACITY ASSESSMENT

6

What is the nationality of those US presidents?

  • d1. Edward

Dickinson Baker d2. Barack Obama

  • d3. Bill

Clinton British Kenyan American American American American American British American USA USA S1 S2 S3 S4 d1:nat S1 <British, Kenyan, American> S2 <American, British, American> S3 <American, American, American> S4 <USA, USA, American> d2:nat d3:nat American USA USA

slide-7
SLIDE 7

American USA USA

VERACITY ASSESSMENT

7

What is the nationality of those US presidents?

  • d1. Edward

Dickinson Baker d2. Barack Obama

  • d3. Bill

Clinton British Kenyan American American American American American British American S1 S2 S3 S4 S1 <British, Kenyan, American> S2 <American, British, American> S3 <American, American, American> S4 <USA, USA, American> Source reliability Fact confidence

+

d1:nat d2:nat d3:nat

slide-8
SLIDE 8

VERACITY ASSESSMENT APPROACHES: LIMITATIONS

8

 Single-Truth S1: <d1:nat, British> is also true.

S1 <British, Kenyan, American> S2 <American, British, American> S3 <American, American, American> S4 <USA, USA, American> d1:nat d2:nat d3:nat

slide-9
SLIDE 9

VERACITY ASSESSMENT APPROACHES: LIMITATIONS

9

 Single-Truth S1: <d1:nat, British> is also true.

  • No contextual information

S1: <d1:nat, British> is true in the temporal context [1811-1816] S1: <d1:birthdate, 1811> S1: <d1:birthPlace, London> S1: <d1:immigrationDate, 1816>

S1 <British, Kenyan, American> S2 <American, British, American> S3 <American, American, American> S4 <USA, USA, American> d1:nat d2:nat d3:nat

slide-10
SLIDE 10

VERACITY ASSESSMENT APPROACHES: LIMITATIONS

10

 Single-Truth S1: <d1:nat, British> is also true.

  • No contextual information

S1: <d1:nat, British> is true in the temporal context [1811-1816] S1: <d1:birthdate, 1811> S1: <d1:birthPlace, London> S1: <d1:immigrationDate, 1816>

  • Some sources mainly created from data

extracted from Wikipedia How reliable S1: <d1:nat, British> is? S1: <d1:birthPlace, London> S1: <d1:immigrationDate, 1816>

S1 <British, Kenyan, American> S2 <American, British, American> S3 <American, American, American> S4 <USA, USA, American> d1:nat d2:nat d3:nat

slide-11
SLIDE 11

VERACITY ASSESSMENT APPROACHES: LIMITATIONS

11

  • No explanations

Why S1: <d1:nat, British> is true? S1: <d1:birthPlace, London>

S1 <British, Kenyan, American> S2 <American, British, American> S3 <American, American, American> S4 <USA, USA, American> d1:nat d2:nat d3:nat

slide-12
SLIDE 12

GOAL

Build an approach to assess the veracity of facts taken from knowledge bases based on spatio-temporal information. 12

slide-13
SLIDE 13

YAGO KNOWLEDGE BASE

 General purpose semantic knowledge base (KB)

Integrates information extracted from Wikipedia infoboxes, WordNet, and GeoNames

> 10 million entities (persons, cities, organizations),

> 120 million facts about these entities  Attaches temporal and spatial dimensions to many of its facts and entities – meta facts.

13

Yago structure

slide-14
SLIDE 14

APPROACH: RULE BASED TEMPORAL META FACTS GENERATION

14

slide-15
SLIDE 15

RULE BASED TEMPORAL META FACTS GENERATION

Focus on facts that may change over time:

Brad Pitt acted in

 the Fight Club in 1999  the Curious Case of Benjamin Button in 2008

Paul McCartney was/is married with

 Heather Mills from 2002 to 2008  Nancy Shevell since 2011

15

slide-16
SLIDE 16

BASIC ALGORITHM TO INFER META FACTS

16

slide-17
SLIDE 17

TIMESTAMP GENERATION RULE

17

slide-18
SLIDE 18

TIMESTAMP GENERATION RULE

18

slide-19
SLIDE 19

TIMESTAMP GENERATION RULE

19

slide-20
SLIDE 20

TIMESTAMP GENERATION RULE

20

slide-21
SLIDE 21

TEMPORAL INTERVAL RULE

21

slide-22
SLIDE 22

TEMPORAL INTERVAL RULE

22

slide-23
SLIDE 23

23

TEMPORAL INTERVAL RULE

validAfter

slide-24
SLIDE 24

24

TEMPORAL INTERVAL RULE

slide-25
SLIDE 25

25

TEMPORAL INTERVAL RULE

slide-26
SLIDE 26

26

TEMPORAL INTERVAL RULE

slide-27
SLIDE 27

CASE STUDY: MOVIE DOMAIN (YAGO)

27

slide-28
SLIDE 28

 Yago:

# of films: 151427

# of actors in Yago: 47800

# of release dates available: 136234

MOVIE DOMAIN (YAGO)

28

slide-29
SLIDE 29

RESULTS: actedIn

29

slide-30
SLIDE 30

RESULTS: actedIn

30

  • 8 MFs not inferred because some facts don’t have release date associated.
  • 23 share the same information (Yago MFs & IMDb)
  • Results vs Yago MFs & IMDb:
  • 16 have the same IMDb information

Notice: Yago MFs are more accurate.

slide-31
SLIDE 31

RESULTS: actedIn

  • 8 MFs not inferred because some facts don’t have release date associated.
  • 23 share the same information (Yago MFs & IMDb)
  • Results vs Yago MFs & IMDb:
  • 16 have the same IMDb information

Notice: Yago MFs are more accurate.

31

slide-32
SLIDE 32

RESULTS: wroteMusicFor

32

slide-33
SLIDE 33

RESULTS: wroteMusicFor

  • 118 MFs not inferred because some facts don’t have release date associated.
  • 3 share the same information (Yago MFs & IMDb)
  • Results vs Yago MFs & IMDb:

33

slide-34
SLIDE 34

ONGOING WORK:

 Qualitative evaluation of the meta facts inferred.  Creating new set of rules.  Extend the approach to reason more globally on the whole graph while inferring meta facts.  Spatial reasoning.

 E.g.: Film release dates are associated to specific locations

(country, city).  (Semi-)automatic approach for rule generation.

FUTURE WORK:

34

slide-35
SLIDE 35

MERCI !

35