Towards Robust Abstractive Multi-Document Summarization thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Towards Robust Abstractive Multi-Document Summarization

Published on Oct 02, 20132793 Views

In automatic summarization, centrality is the notion that a summary should contain the core parts of the source text. Current systems use centrality, along with redundancy avoidance and some sentence

Related categories

Chapter list

Towards Robust Abstractive Multi-Document Summarization: A Caseframe Analysis of Centrality and Domain00:00
Centrality and Extraction00:02
Limits of Extraction00:45
Message of This Paper02:24
Previous Studies on Summarization03:07
More Related Studies04:04
Novelty of Our Studies04:46
Overview of Studies05:36
Unit of Analysis: Caseframes06:38
Example07:44
Data set09:14
Peer Comparison Conditions10:15
Study 1: Sentence Aggregation - 111:08
Study 1: Sentence Aggregation - 212:35
Study 1: Sentence Aggregation - 314:07
Study 2: Signature Caseframes14:27
Signature Caseframe Density - 115:58
Signature Caseframe Density - 216:55
Accounting for Paraphrasing17:14
Consequences18:10
Study 3: Summary Reconstruction18:47
Reconstruction from Source Text - 119:21
Reconstruction from Source Text - 219:37
Adding In-domain Articles19:49
Conclusions20:21
Using Domain Knowledge20:50