arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0803.2856cs.CLcs.LG
收藏

Figuring out Actors in Text Streams: Using Collocations to establish Incremental Mind-maps

Johann Wolfgang Goethe-University Frankfurt am Main(法兰克福约翰·沃尔夫冈·歌德大学);University of Luxembourg(卢森堡大学)

T. Rothenberger, S. Oez, E. Tahirovic, C. Schommer

英文摘要:

The recognition, involvement, and description of main actors influences the story line of the whole text. This is of higher importance as the text per se represents a flow of words and expressions that once it is read it is lost. In this respect, the understanding of a text and moreover on how the actor exactly behaves is not only a major concern: as human beings try to store a given input on short-term memory while associating diverse aspects and actors with incidents, the following approach represents a virtual architecture, where collocations are concerned and taken as the associative completion of the actors' acting. Once that collocations are discovered, they become managed in separated memory blocks broken down by the actors. As for human beings, the memory blocks refer to associative mind-maps. We then present several priority functions to represent the actual temporal situation inside a mind-map to enable the user to reconstruct the recent events from the discovered temporal results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑