MOMENT: Temporal Meta-Fact Generation and Propagation in Knowledge Graphs [F. Saïs, J. E. Gonzales Malaverri and G. Quercini @ACM-SAC-SWA 2020]
This paper deals with the problem of temporal meta-fact genera- tion in RDF knowledge graphs (KGs). These temporal meta-facts represent the time validity of facts, for instance, <Barack Obama, presidentOf, United States of America> is valid for the period [2008..2016]. We propose an approach called MOMENT that com- bines two methods, the first uses a set of specified rules to generate meta-facts in knowledge bases where no temporal meta-fact exist. The second method exploits existing temporal meta-facts and a set of Horn rules generated by AMIE [9] to propagate the meta-facts and thus expand the set of temporal meta-facts. An experimental evaluation has been conducted using Yago, DBpedia and Wikidata datasets. The obtained results are promising and showed the relevance of such an approach for temporal meta-fact generation in Knowledge Graphs.
TEST BANK For, Information Technology Project Management 9th Edition Kathy Sc...
MOMENT: Temporal Meta-Fact Generation and Propagation in Knowledge Graphs
1. MOMENT – TEMPORAL META-FACT
GENERATION AND PROPAGATION IN
KNOWLEDGE GRAPHS
FATIHA SAÏS, JOANA E. GONZALES MALAVERRI,
AND GIANLUCA QUERCINI
LRI, CNRS & Paris Saclay University, France
ACM SAC-SWA, March 31h, 2020
1
2. KNOWLEDGE GRAPHS (KGS)
"Linking Open Data cloud diagram 2017, by Andrejs Abele, John
P. McCrae, Paul Buitelaar, Anja Jentzsch and Richard Cyganiak.
http://lod-cloud.net/" 2
3. facts
KNOWLEDGE GRAPHS (KGS)
"Linking Open Data cloud diagram 2017, by Andrejs Abele, John
P. McCrae, Paul Buitelaar, Anja Jentzsch and Richard Cyganiak.
http://lod-cloud.net/" 3
.
.
.
6. KG Creation
Information extraction from web pages (DBpedia, Yago),
collaborative (Wikidata), ...
KG Enrichment and Expansion
Content prediction, data fusion, data/knowledge linking, ...
KG Validity
Dealing with errors and ambiguities
Fact validity
Timeliness: truth of statements often changes with time:
E.g., Currently, who is the US president?
KNOWLEDGE GRAPHS: SOME
KEY PROBLEMS
6
7. KGS – WHY TIME MATTERS?
Time period during which a fact is valid: validity time.
f1: <#Obama presidentOf US> is true in the temporal context [2008-2016]
f2: <#Trump presidentOf US> is true in the temporal context [2016-now]
Query answering
Consistency checking
Sort the sequence of facts.
7
8. PROBLEM AND PROPOSED APPROACH
Problem
How can we capture fact validity time using only
the facts and the structure of the KGs?
8
9. PROBLEM AND PROPOSED APPROACH
Problem
How can we capture fact validity time using only
the facts and the structure of the KGs?
Approach – Seed meta-fact generation (step 1)
9Knowledge Patterns
10. PROBLEM AND PROPOSED APPROACH
Problem
How can we capture fact validity time using only
the facts and the structure of the KGs?
Approach – Seed meta-fact generation (step 1)
10Knowledge Patterns
11. PROBLEM AND PROPOSED APPROACH
Temporal meta-fact
Problem
How can we capture fact validity time using only
the facts and the structure of the KGs?
Approach – Seed meta-fact generation (step 1)
11Knowledge Patterns
12. 1. SEED META-FACT GENERATION
Focus on predicates 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
12
13. 1. SEED META-FACT GENERATION
Algorithm: Query generation
For each knowledge pattern, in the form of:
13
14. 1. SEED META-FACT GENERATION
Algorithm: Query generation
For each knowledge pattern, in the form of:
Generate a SPARQL query (graph pattern = rule premise)
14
15. 1. SEED META-FACT GENERATION
Algorithm: Meta-fact generation
On the set of facts obtained from SPARQL queries, generate the
set of temporal meta-facts
15
16. 1. SEED META-FACT GENERATION
Algorithm: Meta-fact generation
On the set of facts obtained from SPARQL queries, generate the
set of temporal meta-facts
For interval knowledge patterns: compute an intersection
between the temporal intervals associated to the subject and the
object of a fact.
16
17. 1. SEED META-FACT GENERATION
Algorithm: Meta-fact generation
On the set of facts obtained from SPARQL queries, generate the
set of temporal meta-facts
For interval knowledge patterns: compute an intersection
between the temporal intervals associated to the subject and the
object of a fact.
Start-date
End-date 17
19. 2. TEMPORAL META-FACT EXPANSION
Use a set of Horn rules (generated by AMIE) to propagate existing
temporal meta-facts
19
20. 2. TEMPORAL META-FACT EXPANSION
Use a set of Horn rules (generated by AMIE) to propagate existing
temporal meta-facts
Step 1: Rule selection and instantiation
Keep only rule with PCA-confidence > theta
Select those premises contain a predicate in the set of seed
meta-facts
Rule instantiation on a set of facts and seed meta-facts
(generated or already existing in the KG)
20
21. 2. TEMPORAL META-FACT EXPANSION
Use a set of Horn rules (generated by AMIE) to propagate existing
temporal meta-facts
Step 2: Temporal meta-fact propagation
Case 1: only one meta-fact in the premise, then propagate the
date attached to the conclusion
Case 2: if several meta-facts in the premise, then apply
temporal combination constraints
21
23. 2. TEMPORAL COMBINATION
CONSTRAINTS
Use of Allen’s interval relationships: during(TI, TI’), overlaps(TI, TI’),
meets(TI, TI’), …
Apply one of the twelve combination constraints we defined, such as:
TI1 TI2
S(TI1) E(TI1)S(TI2) E(TI2)
TI3
S(TI3) E(TI3)
Inferred time interval
23
24. 2. META-FACT CONFIDENCE
Assign for each inferred meta-fact a confidence value in [0;1], using:
Quality scores of the used rule: Head-Coverage, PCA-confidence
K1: #meta-facts associated with the atoms of the rule premise
K2: the sum of the distances between the temporal meta-facts of
the premise
24
26. Yago: contains 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
some facts and entities.
1. SEED META-FACT GENERATION:
EXPERIMENTS ON YAGO
Time-sensitive predicates
26
27. 1. SEED META-FACT GENERATION:
EXPERIMENTS ON YAGO
Quantitative results of seed meta-fact generation
27
x 8479
x 228
x 100
x 6
x 67
28. 1. SEED META-FACT GENERATION:
EXPERIMENTS ON YAGO
Qualitative evaluation on Movie case study
- Use of IMDb as a ground truth
- Comparaison with yago meta-facts IMDb - page
28
29. Movie domain data in YAGO:
# of films: 151427
# of actors: 47800
# of release dates available: 136234
1. SEED META-FACT GENERATION:
EXPERIMENTS ON YAGO
29
30. 1. SEED META-FACT GENERATION:
EXPERIMENTS ON YAGO
Evaluation of 5200 meta-facts of actedin predidcate
Movie-title and actor-name equal IMDb title and one of the
IMDb actors’ name
25% of release date in Yago are different with IMDb release
date: premiere date in IMDb and shown in a festival date in
yago
30
31. 1. SEED META-FACT GENERATION:
EXPERIMENTS ON YAGO
Evaluation of 5200 meta-facts of actedin predidcate
Movie-title and actor-name equal IMDb title and one of the
IMDb actors’ name
25% of release date in Yago are different with IMDb release
date: premiere date in IMDb and shown in a festival date in
yago
Results:
Reach of 75% of precision for timestamp meta-facts.
Some meta-facts are not inferred, some films have no release
date in Yago.
Some obtained interval meta-facts are too large: need to be
refined
31
32. 2. TEMPORAL META-FACT
EXPANSION: EXPERIMENTS
Dbpedia as a KG to be enriched with temporal meta-facts
As seed meta-facts:
Yago meta-facts: datasets A
Seed meta-facts: dataset B
Use of AMIE horn rules
Wikidata as a ground truth (qualifiers)
Use of Wikidata endpoint *
* https://query.wikidata.org/ 32
35. 2. TEMPORAL META-FACT
EXPANSION: EXPERIMENTS
Qualitative results: Considered timestamp meta-facts and full date
Dataset A gets better results: better accuracy of seed meta-facts
Dataset B reaches 0.67 of F-measure
35
36. CONCLUSION
An approach for seed temporal meta-fact
generation for time-sensitive predicates
A rule-based approach for temporal meta-fact
propagation
A first quantitative and qualitative evaluation
36
37. FUTURE WORK
Develop an approach to learn time-sensitive (evolving)
predicates.
Improvements are needed for seed interval meta-facts
generation
Fact validity assessment using temporal-meta facts
Combine temporal and spatial reasoning:
E.g.: Film release dates are associated to specific
locations (country, city).
37
39. MOMENT –TEMPORAL META-FACT
GENERATION AND PROPAGATION IN
KNOWLEDGE GRAPHS
FATIHA SAÏS, JOANA E. GONZALES MALAVERRI,
AND GIANLUCA QUERCINI
LRI, CNRS & Paris Saclay University, France
ACM SAC-SWA, March 31h, 2020
39