.png){kind=icon}
.png){kind=icon}
Return
Using Topic Themes for Multi-Document Summarization
.png){kind=icon}
PRE
AI
DOI：10.1145/1777432.1777436.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The problem of using topic representations for multidocument summarization (MDS) has received considerable attention recently. Several topic representations have been employed for producing informative and coherent summaries. In this article, we describe five previously known topic representations and introduce two novel representations of topics based on topic themes. We present eight different methods of generating multidocument summaries and evaluate each of these methods on a large set of topics used in past DUC workshops. Our evaluation results show a significant improvement in the quality of summaries based on topic themes over MDS methods that use other alternative topic representations.
Keywords:
Algorithms
Performance
Experimentation
Summarization
topic representations
topic themes
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.1
Papers:
1.2K
Citations:
4.7K