Refining Imprecise Spatio-temporal Events: A Network-based Approach - - PowerPoint PPT Presentation

▶
refining imprecise spatio temporal events a network based
SMART_READER_LITE
LIVE PREVIEW

Refining Imprecise Spatio-temporal Events: A Network-based Approach - - PowerPoint PPT Presentation

May 02, 2023 133 likes •476 views

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 1 , Johanna Gei 1 , Michael Gertz 1 , Stefan Hagedorn 2 and Kai-Uwe Sattler 2 1 Heidelberg University, Institute of Computer Science Database Systems Research

slide-1
SLIDE 1

Refining Imprecise Spatio-temporal Events: A Network-based Approach

Andreas Spitz1, Johanna Geiß1, Michael Gertz1, Stefan Hagedorn2 and Kai-Uwe Sattler2

1 Heidelberg University, Institute of Computer Science

Database Systems Research Group, Heidelberg

2Technical University of Ilmenau

Databases and Information Systems Group, Ilmenau {spitz, geiss, gertz}@informatik.uni-heidelberg.de {stefan.hagedorn, kus}@tu-ilmenau.de

10th GIR Workshop San Francisco, , 2016

slide-2
SLIDE 2

Motivation Event Networks Event Refinement Evaluation Summary Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 1 of 23

slide-3
SLIDE 3

Motivation Event Networks Event Refinement Evaluation Summary

What is an Event?

Event

“The Jimi Hendrix Experience toured Germany in 1967.”

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 2 of 23

slide-4
SLIDE 4

Motivation Event Networks Event Refinement Evaluation Summary

What is an Event?

Event

“The Jimi Hendrix Experience toured Germany in 1967.”

Definition: Event

“Something that happens at a given place and time between a group of actors.”

[All02]

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 2 of 23

slide-5
SLIDE 5

Motivation Event Networks Event Refinement Evaluation Summary

Event Triangles

Intuition:

  • Events correspond to triangular

structures of entities

  • Participating entities can be used to

extract events

  • Linguistic, sentence-based event

detection can improve results

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 3 of 23

slide-6
SLIDE 6

Motivation Event Networks Event Refinement Evaluation Summary

Event Extraction

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 4 of 23

slide-7
SLIDE 7

Motivation Event Networks Event Refinement Evaluation Summary

Event Extraction

Generating weights for events:

  • Similarity of entities [GSG15]:

φ(r, r′) := exp

  • − dist(r,r′)

2

  • Refining Imprecise Spatio-temporal Events: A Network-based Approach

Andreas Spitz 4 of 23

slide-8
SLIDE 8

Motivation Event Networks Event Refinement Evaluation Summary

Event Extraction

Generating weights for events:

  • Similarity of entities [GSG15]:

φ(r, r′) := exp

  • − dist(r,r′)

2

  • Weight of individual events:

ω(ei) = min{φ(l, t), φ(l, a), φ(t, a)}

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 4 of 23

slide-9
SLIDE 9

Motivation Event Networks Event Refinement Evaluation Summary

Event Extraction

Generating weights for events:

  • Similarity of entities [GSG15]:

φ(r, r′) := exp

  • − dist(r,r′)

2

  • Weight of individual events:

ω(ei) = min{φ(l, t), φ(l, a), φ(t, a)}

  • Weight of aggregated events:

ω(e) := k

i=1 ω(ei)

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 4 of 23

slide-10
SLIDE 10

Motivation Event Networks Event Refinement Evaluation Summary

Geographic Background Network

Locations can be connected in a location network GL based on:

  • Geographic containment
  • Geographic neighbourhood
  • Reachability
  • Semantic similarity
  • Context-dependent relations

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 5 of 23

slide-11
SLIDE 11

Motivation Event Networks Event Refinement Evaluation Summary

Temporal Background Network

Dates are inherently connected in a temporal network GT :

  • Temporal containment is straightforward
  • Heterogeneous granularity levels are possible

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 6 of 23

slide-12
SLIDE 12

Motivation Event Networks Event Refinement Evaluation Summary

Social Background Network

Actors form a social network GA and are connected by:

  • Acquaintance or Relation
  • Collaboration
  • Organization membership
  • Context-dependent similarities

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 7 of 23

slide-13
SLIDE 13

Motivation Event Networks Event Refinement Evaluation Summary

Event Hypergraph

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 8 of 23

slide-14
SLIDE 14

Motivation Event Networks Event Refinement Evaluation Summary

Event Hypergraph

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 8 of 23

slide-15
SLIDE 15

Motivation Event Networks Event Refinement Evaluation Summary

Event Hypergraph

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 8 of 23

slide-16
SLIDE 16

Motivation Event Networks Event Refinement Evaluation Summary

Event Refinement

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 9 of 23

slide-17
SLIDE 17

Motivation Event Networks Event Refinement Evaluation Summary

Event Refinement

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 10 of 23

slide-18
SLIDE 18

Motivation Event Networks Event Refinement Evaluation Summary

Granularity Refinement

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 11 of 23

slide-19
SLIDE 19

Motivation Event Networks Event Refinement Evaluation Summary

Neighbourhood Refinement

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 12 of 23

slide-20
SLIDE 20

Motivation Event Networks Event Refinement Evaluation Summary

Neighbourhood Refinement

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 12 of 23

slide-21
SLIDE 21

Motivation Event Networks Event Refinement Evaluation Summary

Event Refinement: Stratification

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 13 of 23

slide-22
SLIDE 22

Motivation Event Networks Event Refinement Evaluation Summary

Evaluation

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 14 of 23

slide-23
SLIDE 23

Motivation Event Networks Event Refinement Evaluation Summary

Extraction of Events from Wikipedia

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 15 of 23

slide-24
SLIDE 24

Motivation Event Networks Event Refinement Evaluation Summary

Entities and Events by Window Size

1 2 3 4 ·108 number of events |E| 1 2 4 6 8 10 2 4 6 8 ·105 window size w number of entities |A| |L| |T|

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 16 of 23

slide-25
SLIDE 25

Motivation Event Networks Event Refinement Evaluation Summary

Background Network Construction

Location Network:

  • From Wikidata: continents, countries and cities
  • Containment edges between hierarchy levels
  • Neighbourhood edges between adjacent countries
  • Neighbourhood edges between close cities

Temporal Network:

  • Temporal Tagging with Heideltime [SG13]
  • Containment edges between years, months and days
  • Neighbourhood edges within granularity layers

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 17 of 23

slide-26
SLIDE 26

Motivation Event Networks Event Refinement Evaluation Summary

Ground Truth Event Queries

We obtain events by

  • Named Entity Recognition in
  • nline news articles
  • Extraction of the entity triples
  • f events by hand

We generate queries by making events less certain in the combination of dimensions

  • Location L
  • Time T
  • Granularity g
  • Neighbourhood n

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 18 of 23

slide-27
SLIDE 27

Motivation Event Networks Event Refinement Evaluation Summary

Evaluation Results (Precision)

1 2 4 6 8 10 0.2 0.4 0.6 0.8 1 window size w MAP Tg Lg TgLg Tn Ln TnLn TgLn TnLg

  • rig

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 19 of 23

slide-28
SLIDE 28

Motivation Event Networks Event Refinement Evaluation Summary

Evaluation Results (Recall)

1 2 4 6 8 10 0.4 0.6 0.8 1 window size w Recall Tg Lg TgLg Tn Ln TnLn TgLn TnLg

  • rig

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 20 of 23

slide-29
SLIDE 29

Motivation Event Networks Event Refinement Evaluation Summary

Summary

New method for event representation:

  • As a hypergraph model
  • Backed by underlying entity networks
  • Compatible with any entity-based definition of event

Graph-based event refinement offers:

  • Spatio-temporal refinement in two dimensions:

neighbourhood and granularity

  • Efficient computation due to localized queries
  • Language independence

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 21 of 23

slide-30
SLIDE 30

Motivation Event Networks Event Refinement Evaluation Summary

Ongoing Work

Directions for ongoing event refinement research:

  • Include measures of granularity and neighbourhood in social

background networks

  • Include hierarchical or organization networks
  • Add event structures beyond triangles

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 22 of 23

slide-31
SLIDE 31

Motivation Event Networks Event Refinement Evaluation Summary

The event network and the background networks are available for download. http://dbs.ifi.uni-heidelberg.de/index.php?id=data

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 23 of 23

slide-32
SLIDE 32

Motivation Event Networks Event Refinement Evaluation Summary

The event network and the background networks are available for download. http://dbs.ifi.uni-heidelberg.de/index.php?id=data Thank you! Questions?

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 23 of 23

slide-33
SLIDE 33

Motivation Event Networks Event Refinement Evaluation Summary

Bibliography

James Allan. Topic Detection and Tracking: Event-Based Information Organization, volume 12. Springer Science & Business Media, 2002. Johanna Geiß, Andreas Spitz, and Michael Gertz. Beyond Friendships and Followers: The Wikipedia Social Network. In ASONAM, 2015. Jannik Str¨

  • tgen and Michael Gertz.

Multilingual and cross-domain temporal tagging. Language Resources and Evaluation, 47(2), 2013. Denny Vrandeˇ ci´ c and Markus Kr¨

  • tzsch.

Wikidata: A Free Collaborative Knowledgebase. Communications of the ACM, 57(10), 2014.

Refining Imprecise Spatio-temporal Events: A Network-based Approach Andreas Spitz 23 of 23