Abstract
Experiences with and Reflections on Text Summarization Tools
Highlights
Text and natural language processing capabilities are of increasing importance in the information society of today
Evaluation methods can be divided into extrinsic and intrinsic: extrinsic evaluation being task-based evaluation through investigating how a summary affects the completion of some task, and intrinsic evaluation being content based examination by comparing a summary to a target
Examples of extrinsic evaluation work can be found in Ref. 24 and Ref. 25
Summary
Different extractive methods make use of different text features to represent the text content These features may include: thematic features based on term frequency statistics, location features such as position in the text, position in the paragraph or the particular section, background features such as terms from title and headings in the text, cue words and phrases such as intext summary cues “in summary”, “our investigation”, bonus and stigma terms such as “significant”, “impossible”, and so on. Such features can be analyzed individually or combined selectively to form a function that is used to identify important words and significant sentences in the text. Sentences that are concentrates of high score words (significant words) are often the target sentences to be extracted
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: International Journal of Computational Intelligence Systems
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.