READING: A Self Sufficient Internet News System with Applications in Information and Knowledge Mining

Bracewell, David B.; Ren, Fuji; Hisazumi, K.; Teng, Zhi; Furose, Y.; Kuroiwa, Shingo

doi:10.1109/nlpke.2007.4368032

Cited by 3 publications

(3 citation statements)

References 6 publications

(1 reference statement)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system aggregates news from around the world and then automatically processes the news. The automatic processing takes care of traditional news ideas, such as classifying the categories the articles are in, determining the topic of the articles and extracting keywords to help identify important concepts [7]. It goes beyond the traditional, though, by recognizing named entities, determining where the news took place, and allowing for a linking of the information in one article with the information in others.…”

Section: Introductionmentioning

confidence: 99%

Notice of Violation of IEEE Publication Principles: A foundation for knowledge system with application in information retrieval and knowledge acquisition

Teng

Liu

Ren

2008

2008 International Conference on Natural Language Processing and Knowledge Engineering

View full text Add to dashboard Cite

In this paper we present a knowledge system, which is a self sufficient system for aggregating, extraction and classifying news from around the world. This paper present some algorithms for monitoring and gathering news from RSS and websites, creating special domain corpora. The system, however, goes beyond the traditional news aggregation sites by mining information and knowledge from the news articles to aid in such tasks as decision making. The system is able to collect, classify and mine knowledge automatically without the need for an editor or intervention by an administrator. As knowledge system, average users, news professionals and researchers alike will find that the system offers something for them. Our work shows that better performance is achieved and the result showed that this method has potential in this field.

show abstract

Section: Introductionmentioning

confidence: 99%

Notice of Violation of IEEE Publication Principles: A foundation for knowledge system with application in information retrieval and knowledge acquisition

Teng

Liu

Ren

2008

2008 International Conference on Natural Language Processing and Knowledge Engineering

View full text Add to dashboard Cite

show abstract

“…We cannot evaluate our system using the NIST because we did not participate in the Document Understanding Conferences (DUC). 4 In order to evaluate our proposed approach, we used two evaluation criterions that proved effective for summary evaluation in Chinese, VPercent and HPercent [15]. VPercent is the coverage ratio of valid word (exclude stopwords).…”

Section: Text Summarization Evaluationmentioning

confidence: 99%

“…Today, the web is being increasingly used as an information source in the NLP field. Several researchers have explored the potential of web data for information collection [4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Create Special Domain News Collections through Summarization and Classification

Teng

Liu

Ren

2009

IEEJ Transactions Elec Engng

Self Cite

View full text Add to dashboard Cite

In this paper, we present a novel technique to create a special domain news collection system from really simple syndication (RSS) news sites through summarization and classification. The main aim of this research is to build a self-sufficient news collection system in disaster domain. In this news collection system, we used new strategies and algorithms to mine news from RSS sites, recognized and collected disaster news using automatic summarization and classification. The most striking dissimilarity between our study and previous work is that we use a novel summary approach to improve the classification performance. This paper discusses the effect of summarization and classification model on system performance. Results show that our method yields a better performance in this field. 

show abstract