0.25
0.5
0.75
1.25
1.5
1.75
2
Leveraging Pre-trained Language Models for Time Interval Prediction in Text-Enhanced Temporal Knowledge Graphs
Published on Jun 14, 202484 Views
Most knowledge graph completion (KGC) methods rely solely on structural information, even though a large number of publicly available KGs contain additional temporal (validity time intervals) and text
Related categories
Chapter list
Pre-trained Language Models for Time Interval Prediction in Text-Enhanced Temporal Knowledge Graphs00:00
Knowledge Graph00:09
Temporal KG00:18
Text-Enhanced TKG00:48
Temporal KG completion01:22
Time Interval Prediction02:30
Pre-trained Language Models03:35
PLM+KG05:40
Our Approach07:37
The idea07:49
TEMT Framework - 108:09
TEMT Framework - 208:48
Text Encoder09:43
Time Encoder10:28
TEMT Framework - 311:24
Training11:45
Inference12:28
Evaluation - 113:26
Evaluation - 213:36
Experiments14:30
Results - transductive15:34
Results - inductive16:09
Results - transductive16:39
Further Diagnosis16:45
TEMT16:59