Filters








221,477 Hits in 7.7 sec

Automatic Extraction of Publication Time from News Search Results

Yiyao Lu, Weiyi Meng, Wanjing Zhang, King-Lup Liu, Clement Yu
2006 22nd International Conference on Data Engineering Workshops (ICDEW'06)  
For news search engines, the publication time of news items can usually be found in the returned search result records.  ...  In this paper, we introduce a method that can automatically extract the publication time for each news story returned from news search engines based on several important observations we made.  ...  Acknowledgement: This work is supported in part by fundings from the following sources: Webscalers, NSF grants IIS-0414981, IIS-0414939 and CNS-0454298.  ... 
doi:10.1109/icdew.2006.35 dblp:conf/icde/LuMZLY06 fatcat:a2s6mndsh5e2xmburozsiuhxtq

TimeMachine: Entity-centric Search and Visualization of News Archives [article]

Pedro Saleiro, Jorge Teixeira, Carlos Soares, Eugénio Oliveira
2016 arXiv   pre-print
from co-occurrences networks extracted from the news articles.  ...  From the computational journalism perspective, TimeMachine allows users to explore media content through time using automatic identification of entity names, jobs, quotations and relations between entities  ...  When selecting an entity from the ranked list of results, users access the entity profile page which containing a set of automatically extracted entity specific data: name, profession, a set of news articles  ... 
arXiv:1601.00855v1 fatcat:xhf2wnkfyjgijkb7lfhi335p24

Extended Vulnerability Feature Extraction Based on Public Resources

Yulia Tatarinova, Olga Sinelnikova
2019 Theoretical and Applied Cybersecurity  
The focus of this research is to define a framework that automatically analyses Common Vulnerabilities and Exposures (CVE) from public and disclosed resources and makes mapping to the target computer system  ...  In this paper, we describe the main vulnerability feature set, provide approaches for automatic extraction from databases and open resources.  ...  Characteristics from public resources and news, Name Description Definition Extraction approaches References Public references NVD db parsing, web search Exploit References with exploit information  ... 
doi:10.20535/tacs.2664-29132019.1.169085 fatcat:4z2dfcpqcjaerppoawcwp6saje

AllInOneNews

King-Lup Liu, Weiyi Meng, Jing Qiu, Clement Yu, Vijay Raghavan, Zonghuan Wu, Yiyao Lu, Hai He, Hongkun Zhao
2007 Proceedings of the 2007 ACM SIGMOD international conference on Management of data - SIGMOD '07  
This paper also reports the results of a comparative evaluation of three commercial news search systems, one search engine -Google News and two metasearch engines -Mamma News and AllInOneNews.  ...  Another contribution of this paper is that we introduce a novel scheme to compare multiple news search systems in a combined measure that takes both relevance and time-sensitivity of retrieved information  ...  The search engine selection algorithm adopted by AllInOneNews is a revised version of the optimal ranking algorithm described in [18, 24] . This method is summarized below:  ... 
doi:10.1145/1247480.1247601 dblp:conf/sigmod/LiuMQYRWLHZ07 fatcat:xyu6xslcz5e7xpyk7usjqo5pyi

The Automatic Extraction of Web Information Based on Regular Expression

Li Ji, Jiang Guangyu, Xu Aijun, Wang Yunzhen
2017 Journal of Software  
And realized the algorithm of locating and automatically extracting multi-web Baidu news information.  ...  Finally, the method of multi-page location retrieval and structured extraction based on search engine is realized.  ...  engine n's searching results for public truncated strings of the URL; n is the search engine; i is the search result page number; pn(i)n is the paging function of the search engine n ;Keyword (i)mn is  ... 
doi:10.17706/jsw.12.3.180-188 fatcat:uqq62anncrhd7piswluryvclnu

An automatic method for extracting citations from Google Books

Kayvan Kousha, Mike Thelwall
2014 Journal of the Association for Information Science and Technology  
In response, this article introduces a method to automatically remove false and irrelevant matches from GB citation searches in addition to introducing refinements to a previous GB manual citation extraction  ...  The method was evaluated by manual checking of sampled GB results and comparing citations to about 14,500 monographs in the Thomson Reuters Book Citation Index (BKCI) against automatically extracted citations  ...  An early and partial version of the automated method described in this article was used but not tested in a previous paper (Abdullah & Thelwall, in press).  ... 
doi:10.1002/asi.23170 fatcat:jmlbojosuzg6pkfuivxuphogwq

A Text Mining Approach to Analyze Public Media Science Coverage and Public Interest in Science

Ying Sun
2014 International Journal of Machine Learning and Computing  
The two sets of data are compared and correlated to identify any relationship between traditional media and the new media in impacting public perceptions of new scientific developments and public's general  ...  Index Terms-Data mining, civic science literacy, public interest in science, mass media. Ying Sun received her B.S. degree in information science from Peking University in 1996.  ...  We assembled our corpus by extracting from LexisNexis database about 19K articles from The New York Times, and 8K TV news scripts from ABC news, CBS news, Fox news and NBC news published form the years  ... 
doi:10.7763/ijmlc.2014.v6.461 fatcat:krrev2ki7nhpphbf3g7d33laq4

Semantic dispatching of multimedia news with MEWS

Julien Law-To, Gregory Grefenstette, Rémi Landais
2013 Proceedings of the 21st ACM international conference on Multimedia - MM '13  
Here we present MEWS, a Multimedia nEWS platform, which enriches news browsing according to media (text, images, and video) and to automatically detected type of news (music, general news, politics).  ...  Recent advances in semanticallyrich text processing, in speech-to-text processing, and in image processing allows us to develop new ways of presenting and enriching news stories.  ...  Here the query 'Korea' produces results from Wikipedia, from text-based new stories, from automatic transcriptions of news broadcasts, and from tagged images.  ... 
doi:10.1145/2502081.2502253 dblp:conf/mm/Law-ToGL13 fatcat:myddpsfnovhffp2psufacuesle

Assessing the citation impact of books: The role of Google Books, Google Scholar, and Scopus

Kayvan Kousha, Mike Thelwall, Somayeh Rezaie
2011 Journal of the American Society for Information Science and Technology  
In response, this article introduces a method to automatically remove false and irrelevant matches from GB citation searches in addition to introducing refinements to a previous GB manual citation extraction  ...  The method was evaluated by manual checking of sampled GB results and comparing citations to about 14,500 monographs in the Thomson Reuters Book Citation Index (BKCI) against automatically extracted citations  ...  An early and partial version of the automated method described in this article was used but not tested in a previous paper (Abdullah & Thelwall, in press).  ... 
doi:10.1002/asi.21608 fatcat:qqgxb23d5zfbzdlowcnxbowmum

DiLiA – The Digital Library Assistant [chapter]

Kathrin Eichler, Holmer Hemsen, Günter Neumann, Norbert Reithinger, Sven Schmeier, Kinga Schumacher, Inessa Seifert
2010 Lecture Notes in Computer Science  
and multi word terms -as well as the extraction of binary relations based on the extracted terms.  ...  In DiLiA we follow a hybrid information extraction approach -a combination of metadata and document processing.  ...  Acknowledgment The research project DiLiA is co-funded by the European Regional Development Fund (ERDF) in context of Investitionsbank Berlin's ProFIT program under grant number 10140159.  ... 
doi:10.1007/978-3-642-15464-5_75 fatcat:ssin6sfrb5fpfcw24fgd3nodry

The Searchbench - Combining Sentence-semantic, Full-text and Bibliographic Search in Digital Libraries

Ulrich Schäfer, Bernd Kiefer, Christian Spurk, Jörg Steffen, Rui Wang, Benjamin Weitz, Magdalena Wolska
2013 Liber Quarterly: The Journal of European Research Libraries  
These have been extracted automatically from metadata and paper texts.  ...  Moreover, negated statements can be excluded from the search results, and negated antonym predicates again count as synonyms (e.g. not include = exclude).  ...  of the world-wide DELPH-IN consortium.  ... 
doi:10.18352/lq.8091 fatcat:rpzajleqlbdito3mwzu7dz7sga

Evolving Knowledge Extraction From Online Resources

Zhibo Xiao, Tharini Nayanika De Silva, Kezhi Mao
2017 Zenodo  
In this paper, we present an evolving knowledge extraction system named AKEOS (Automatic Knowledge Extraction from Online Sources).  ...  The evolving learning module automatically schedules and performs repeated one-time learning to extract the newest information and track the development of an event.  ...  Even for the result of a single query on a search engine, it is hard to quickly grasp the key information underlying the returned search results.  ... 
doi:10.5281/zenodo.1130979 fatcat:q63qm62iuvh3hmqousm7ltgx2m

Automatic Release Notes Generation: A Systematic Literature Review

Mubashir Ali, M. Irtaza Nawaz Tarar, Wasi Haider Butt
2020 2020 IEEE 23rd International Multitopic Conference (INMIC)  
Generating them manually prone to errors and time consuming as it contains a description of new features, bug fixes, license changes, deprecated libraries, new Application Program Interface (API), and  ...  There are different tools available to generate RNs automatically from issue tracker and source code repositories.  ...  Limitations of our study are that we limited our study to just include the of software projects.  ... 
doi:10.1109/inmic50486.2020.9318191 fatcat:s2nwee6hmjchpmiirtzkucobhe

Relations, cards, and search templates

Mira Dontcheva, Steven M. Drucker, David Salesin, Michael F. Cohen
2007 Proceedings of the 20th annual ACM symposium on User interface software and technology - UIST '07  
Finally, we introduce a novel search paradigm that leverages the relationships in a card to direct search queries to extract relevant content from multiple Web sources and fill a new series of cards instead  ...  First, we demonstrate an interface for creating associations between websites, which facilitate the automatic retrieval of related content.  ...  ACKNOWLEDGEMENTS We thank our study participants for spending time with our system and providing useful feedback on future improvements.  ... 
doi:10.1145/1294211.1294224 dblp:conf/uist/DontchevaDSC07 fatcat:bogkqkyhbbdkpjvf73gdg4aboy

A hybrid method for detecting outdated information in Wikipedia infoboxes

Thong Tran, Tru H. Cao
2013 The 2013 RIVF International Conference on Computing & Communication Technologies - Research, Innovation, and Vision for Future (RIVF)  
In this paper, we propose a method to automatically detect outdated attribute values in Wikipedia infoboxes by using facts extracted from the general Web.  ...  Our method uses the pattern-based fact extraction approach. The patterns for fact extraction are automatically learned using a number of available seeds in related Wikipedia infoboxes.  ...  For each seed relation, the top-100 related web pages from the results of the Google engine search are selected, from which patterns are extracted.  ... 
doi:10.1109/rivf.2013.6719874 dblp:conf/rivf/TranC13 fatcat:ih3y45lh4zb2zksf5kjgwmaapu
« Previous Showing results 1 — 15 out of 221,477 results