ESLM: Improving entity summarization by leveraging language models thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

ESLM: Improving entity summarization by leveraging language models

Published on Jun 14, 202463 Views

Entity summarizers for knowledge graphs are crucial in various applications. Achieving high performance on the task of entity summarization is hence critical for many applications based on knowledge g

Related categories

Chapter list

ESLM: Improving Entity Summarization by Leveraging Language Models00:00
Entity Summarization Challenge00:21
Entity Summarization Overview01:27
Motivation02:21
Problem Statement03:28
Related Work04:40
Entity Summarization Using Language Models05:44
Formally definition05:59
Experiment Setup08:05
Comparison with state-of-the-art approaches (F-Measure)08:55
Comparison with state-of-the-art approaches09:46
ESLM is well aligned with the ground truth summary10:20
ESLM provides a wide range of information on the target entity11:23
Highest F-measure performance of BERT, ERNIE, and T5 on ESLM11:57
Highest NDCG scores of BERT, ERNIE, and T5 on ESLM12:57
Conclusion and Future Work13:23
Thank you!14:44