en-es
en
0.25
0.5
0.75
1.25
1.5
1.75
2
Domain-Independent Abstract Generation for Focused Meeting Summarization
Published on Oct 02, 20132343 Views
We address the challenge of generating natural language abstractive summaries for spoken meetings in a domain-independent fashion. We apply Multiple-Sequence Alignment to induce abstract generation te
Related categories
Chapter list
Domain-Independent Abstract Generation for Focused Meeting Summarization00:00
Introduction - 100:10
Introduction - 200:18
Focused Meeting Summarization - 100:40
Focused Meeting Summarization - 201:00
Related Work - 101:35
Goal01:58
Contribution02:11
Related Work - 202:46
Related Work - 303:15
Framework - 103:55
Content Selection04:32
Content Selection via Relation Extraction - 105:04
Content Selection via Relation Extraction - 205:32
Framework - 205:55
Extracting Summary Templates - 106:12
Multiple Sequence Alignment (MSA)06:25
Extracting Summary Templates - 206:56
Extracting Summary Templates - 307:56
Extracting Summary Templates - 508:11
Extracting Summary Templates - 608:16
Extracting Summary Templates - 708:36
Extracting Summary Templates - 808:55
Framework - 309:23
Surface Realization09:32
Template Filling - 109:47
Template Filling - 210:02
Template Filling - 310:11
Full-Constituent Mapping10:24
Sub-Constituent Mapping10:35
Removal10:49
Template Filling - 411:02
Statistical Ranking11:10
Redundancy Handling11:41
Experimental Setup12:01
Content Selection Results - 112:39
Content Selection Results - 213:17
Content Selection Results - 313:59
Content Selection Results - 414:12
Abstract Generation Results - 114:19
Abstract Generation Results - 214:41
Abstract Generation Results - 315:10
Abstract Generation Results - 415:15
Other Results - 115:18
Other Results - 215:28
Human Evaluation16:10
Sample Summary16:39
Conclusion17:09
Thank you17:35
Extracting Summary Templates - 420:05