Event Detection, Evolution and Summarization of Streaming Texts

博士 === 國立臺灣大學 === 電機工程學研究所 === 95 === The World Wide Web (WWW) has become a major information source for people from all walks of life. Although the WWW facilitates information distribution, the ever-increasing volume of Internet documents has made information discovery from the Internet a time cons...

Full description

Bibliographic Details
Main Authors: Chien-Chin Chen, 陳建錦
Other Authors: Ming-Syan Chen
Format: Others
Language:en_US
Published: 2007
Online Access:http://ndltd.ncl.edu.tw/handle/81071177488163825871
id ndltd-TW-095NTU05442125
record_format oai_dc
spelling ndltd-TW-095NTU054421252015-12-07T04:04:13Z http://ndltd.ncl.edu.tw/handle/81071177488163825871 Event Detection, Evolution and Summarization of Streaming Texts 串流文件內涵事件之偵測、演變及摘要之研究 Chien-Chin Chen 陳建錦 博士 國立臺灣大學 電機工程學研究所 95 The World Wide Web (WWW) has become a major information source for people from all walks of life. Although the WWW facilitates information distribution, the ever-increasing volume of Internet documents has made information discovery from the Internet a time consuming task. To manage the massive information of the Internet efficiently, there is a critical need for event detect and summarization methods from text streams. In this dissertation, we provide two adaptive methods to detect sequential events from text streams. We first propose an aging theory to model the life cycle of events. Then, we provide an event detection framework called LIPED which utilizes HMM-based life profiles to predict the activeness status of events for adaptive threshold adjustments. To help user comprehend the development of news topics easily, we also provide a unified mechanism to construct a topic evolution graph and summary from topic documents. The experiment results based on the official TDT4 corpus show that the proposed event detection methods improve the performance of existing well-known event detection approaches substantially, and the composed topic summaries and evolution graphs are highly representative. Ming-Syan Chen 陳銘憲 2007 學位論文 ; thesis 127 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 博士 === 國立臺灣大學 === 電機工程學研究所 === 95 === The World Wide Web (WWW) has become a major information source for people from all walks of life. Although the WWW facilitates information distribution, the ever-increasing volume of Internet documents has made information discovery from the Internet a time consuming task. To manage the massive information of the Internet efficiently, there is a critical need for event detect and summarization methods from text streams. In this dissertation, we provide two adaptive methods to detect sequential events from text streams. We first propose an aging theory to model the life cycle of events. Then, we provide an event detection framework called LIPED which utilizes HMM-based life profiles to predict the activeness status of events for adaptive threshold adjustments. To help user comprehend the development of news topics easily, we also provide a unified mechanism to construct a topic evolution graph and summary from topic documents. The experiment results based on the official TDT4 corpus show that the proposed event detection methods improve the performance of existing well-known event detection approaches substantially, and the composed topic summaries and evolution graphs are highly representative.
author2 Ming-Syan Chen
author_facet Ming-Syan Chen
Chien-Chin Chen
陳建錦
author Chien-Chin Chen
陳建錦
spellingShingle Chien-Chin Chen
陳建錦
Event Detection, Evolution and Summarization of Streaming Texts
author_sort Chien-Chin Chen
title Event Detection, Evolution and Summarization of Streaming Texts
title_short Event Detection, Evolution and Summarization of Streaming Texts
title_full Event Detection, Evolution and Summarization of Streaming Texts
title_fullStr Event Detection, Evolution and Summarization of Streaming Texts
title_full_unstemmed Event Detection, Evolution and Summarization of Streaming Texts
title_sort event detection, evolution and summarization of streaming texts
publishDate 2007
url http://ndltd.ncl.edu.tw/handle/81071177488163825871
work_keys_str_mv AT chienchinchen eventdetectionevolutionandsummarizationofstreamingtexts
AT chénjiànjǐn eventdetectionevolutionandsummarizationofstreamingtexts
AT chienchinchen chuànliúwénjiànnèihánshìjiànzhīzhēncèyǎnbiànjízhāiyàozhīyánjiū
AT chénjiànjǐn chuànliúwénjiànnèihánshìjiànzhīzhēncèyǎnbiànjízhāiyàozhīyánjiū
_version_ 1718146539201757184