Deconstructing Human Literature Reviews - A Framework for Multi-Document Summarization
نویسندگان
چکیده
This study is conducted in the area of multidocument summarization, and develops a literature review framework based on a deconstruction of human-written literature review sections in information science research papers. The first part of the study presents the results of a multi-level discourse analysis to investigate their discourse and content characteristics. These findings were incorporated into a framework for literature reviews, focusing on their macro-level document structure and the sentence-level templates, as well as the information summarization strategies. The second part of this study discusses insights from this analysis, and how the framework can be adapted to automatic summaries resembling human written literature reviews. Summaries generated from a partial implementation are evaluated against human written summaries and assessors’ comments are discussed to formulate recommendations for future work.
منابع مشابه
Systematic literature review of fuzzy logic based text summarization
Information Overloadrq is not a new term but with the massive development in technology which enables anytime, anywhere, easy and unlimited access; participation & publishing of information has consequently escalated its impact. Assisting userslq informational searches with reduced reading surfing time by extracting and evaluating accurate, authentic & relevant information are the primary c...
متن کاملEmpirical analysis of exploiting review helpfulness for extractive summarization of online reviews
We propose a novel unsupervised extractive approach for summarizing online reviews by exploiting review helpfulness ratings. In addition to using the helpfulness ratings for review-level filtering, we suggest using them as the supervision of a topic model for sentence-level content scoring. The proposed method is metadata-driven, requiring no human annotation, and generalizable to different kin...
متن کاملAutomatic Summarization (Mani) Book Review
Researchers in automatic document summarization have already adopted many techniques from existing machine translation literature. Likewise, there is much that the machine translation community can learn from current research in summarization. Automatic Summarization, by Inderjeet Mani, provides a firm grounding in the primary techniques that have been applied to the summarization task, so that...
متن کاملSummary Evaluation with and without References
We study a new content-based method for the evaluation of text summarization systems without human models which is used to produce system rankings. The research is carried out using a new content-based evaluation framework called FRESA to compute a variety of divergences among probability distributions. We apply our comparison framework to various well-established content-based evaluation measu...
متن کاملMultilingual Summarization Evaluation without Human Models
We study correlation of rankings of text summarization systems using evaluation methods with and without human models. We apply our comparison framework to various well-established contentbased evaluation measures in text summarization such as coverage, Responsiveness, Pyramids and ROUGE studying their associations in various text summarization tasks including generic and focus-based multi-docu...
متن کامل