Computer Science – Computation and Language
Scientific paper
2007-10-29
Edited by Galia Angelova, Kalina Bontcheva, Ruslan Mitkov, Nicolas Nicolov, and Nikolai Nikolov, Recent Advances in Natural La
Computer Science
Computation and Language
5 pages, 2 figures
Scientific paper
Despite its importance, the task of summarizing evolving events has received small attention by researchers in the field of multi-document summariztion. In a previous paper (Afantenos et al. 2007) we have presented a methodology for the automatic summarization of documents, emitted by multiple sources, which describe the evolution of an event. At the heart of this methodology lies the identification of similarities and differences between the various documents, in two axes: the synchronic and the diachronic. This is achieved by the introduction of the notion of Synchronic and Diachronic Relations. Those relations connect the messages that are found in the documents, resulting thus in a graph which we call grid. Although the creation of the grid completes the Document Planning phase of a typical NLG architecture, it can be the case that the number of messages contained in a grid is very large, exceeding thus the required compression rate. In this paper we provide some initial thoughts on a probabilistic model which can be applied at the Content Determination stage, and which tries to alleviate this problem.
No associations
LandOfFree
Some Reflections on the Task of Content Determination in the Context of Multi-Document Summarization of Evolving Events does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Some Reflections on the Task of Content Determination in the Context of Multi-Document Summarization of Evolving Events, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Some Reflections on the Task of Content Determination in the Context of Multi-Document Summarization of Evolving Events will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-18941