Главная
Study mode:
on
1
Introduction
2
Background
3
Use Cases
4
Knowledge Graph Construction
5
Overview
6
Calibration
7
Background on Calibration
8
Multiclass calibration
9
Negatives
10
Close World Setting
11
Results
12
Open World Assumption
13
Open World Results
14
Human AI Collaboration
15
Recap
16
Survey
17
Codecs
18
Data Collection
19
Benchmarks
20
Task of Link Prediction
21
Hyperparameter Tuning
22
Triple Classification
23
Codex vs Freebase
24
Rules
25
Summarization
26
Inductive Summarization
27
Model Independent Information
28
RuleBased Model
29
Summary
30
Approach
31
Task Setup
32
Conclusion
33
Codex Benchmark
34
Papers
35
Github Repository
36
Questions
Description:
Explore knowledge graph completion from a practical perspective in this 43-minute conference talk by Danai Koutra at KDD. Dive into the construction, calibration, and evaluation of knowledge graphs in both closed and open world settings. Learn about use cases, human-AI collaboration, and the importance of benchmarks and hyperparameter tuning. Examine the task of link prediction, triple classification, and the comparison between Codex and Freebase. Discover rule-based models, summarization techniques, and inductive approaches. Gain insights into model-independent information and practical applications. Access related papers and the GitHub repository for further exploration.

Revisiting Knowledge Graph Completion From a Practical Perspective - Danai Koutra

Association for Computing Machinery (ACM)
Add to list
0:00 / 0:00