Distilling information from text: The EDS TemplateFiller System

Shuldberg, H. Kelly; Macpherson, Melissa; Humphrey, Pete; Corley, Jamii

doi:10.1002/(sici)1097-4571(199310)44:9<493::aid-asi1>3.0.co;2-m

Cited by 4 publications

(2 citation statements)

References 12 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A different approach to text summarization was applied at EDS Research (Shuldberg, Macpherson, Humphrey, & Corley, 1993). The algorithm filters text into a TemplateFilIer that produces standard form bulletins from raw text input from…”

Section: Smentioning

confidence: 99%

A graphical, self‐organizing approach to classifying electronic meeting output

Orwig

Chen

Nunamaker

1997

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

This dissertation is a milestone to what I hope is a lifetime of continuous learning. My efforts to reach this milestone were made through much cooperation, support, and, sometimes, neglect of family, co-workers, and friends. This dissertation is more than a product of my efforts. It is also a product of the love and emotional support of my wife, Sally, and my daughters, Michaela and Rebecca. In addition to this love and support, I could not have made these efforts without sacrifice on Sally's behalf for the taking of more than her fair share of family obligations as well as financial support. I must also acknowledge the patience and support of my advisor, Dr. Hsinchun Chen. He provided and continues to provide a model of academic excellence in research and teaching. My financial support was provided through a research contract with the United States Army Construction Engineering Research Laboratory. Drs. Jay Nunamaker and Doug Vogel were instrumental in providing guidance and support for obtaining this contract as well as encouragement in developing facilitation skills. I am also indebted to Dr. Windell Ingram, Mark Bovelsky, Lynne Mikulich, the Defense Environmental Security Corporate Information Management office, and many others for their support.

show abstract

Section: Smentioning

confidence: 99%

A graphical, self‐organizing approach to classifying electronic meeting output

Orwig

Chen

Nunamaker

1997

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…State of the art IFS, e.g. Information Lens System [2], EDS Template Filler [3] or Isceen [4] offer a static behavior. A cognitive information system should have the ability to learn and be adapted to the user's behavior.…”

Section: Introductionmentioning

confidence: 99%

Using Genetics in Information Filtering

2013

View full text Add to dashboard Cite

Adaptive filtering of information involves modelling the user's behavior and learning from feedback. This paper describes the design of a cognitive information filtering system that applies (1) linguistic analysis to obtain consistent representations of the contents of messages, (2) an evolutionary algorithm for prioritizing morphologically parsed e-mails and (3) a monitor to simulate cognitive user behavior.

show abstract

Users' perception of the performance of a filtering system

Fidel

Crandall

1997

Proceedings of the 20th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR

View full text Add to dashboard Cite

Abstmd.~though falteringekctronic information is -8 qidly, vq fewstudiesexamined users'perceptions about the success of filtering. Users at the Boeing Company participated in a study which collected data throughobservation, verbal protocols, questionnaire, and interviews. Dsts analysis used four levels of relevance to assess the importance,and fkquency of use, of thirken criteria for relevance, and fourteen for non relevance, that are not topics or subject matters. Results showed that perceived precision ratios for tiltered information were higher then the ratios fbr non-falteredinfbrmatiorLbut not significantly and could still be improved even though most respondents were satisfied with these ratios. Developing methods to create and maintain useful profiles, and finding ways to incorporaterelevance as well as non-relevan= criteria into profdes, are neceswuy to improve the performanceof faltering medumisms.

show abstract

Distilling information from text: The EDS TemplateFiller System

Cited by 4 publications

References 12 publications

A graphical, self‐organizing approach to classifying electronic meeting output

A graphical, self‐organizing approach to classifying electronic meeting output

Using Genetics in Information Filtering

Users' perception of the performance of a filtering system

Contact Info

Product

Resources

About