@inproceedings{bd2f30262d704d06a7f8b0d23175cbbd,
title = "Automatic PDF files based information retrieval system with section selection and key terms aggregation rules",
abstract = "Standard approaches to knowledge extraction from biomedical literature focus on information retrieval from abstracts publicly available in medical databases like PubMed. To limit the number of the results initially, a suitable query against such databases can be constructed. However, for many research topics the pre-selection of small enough set of the documents can be very difficult or even impossible. Another problem stems from large variability of the retrieved lists of publications when changing keywords in search engines. In this paper we address both of these problems by proposing an algorithm and an implementation capable of working on the full text articles. We present an information retrieval system with selection of separate sections of full texts of papers and a rule-based search engine. We demonstrate that in some research our solution can provide much better results than finding documents only by keywords and abstracts.",
keywords = "Information extraction, Knowledge discovery, Natural language processing, Search",
author = "Rafal Lancucki and Andrzej Polanski",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2016.; 4th International Conference on Man{\textendash}Machine Interactions, ICMMI 2015 ; Conference date: 06-10-2015 Through 09-10-2015",
year = "2016",
doi = "10.1007/978-3-319-23437-3\_21",
language = "English",
isbn = "9783319234366",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "251--258",
editor = "Tadeusz Czach{\'o}rski and Aleksandra Gruca and Agnieszka Brachman and Stanis{\l}aw Kozielski and Tadeusz Czach{\'o}rski",
booktitle = "Man{\textendash}Machine Interactions - 4th International Conference on Man{\textendash}Machine Interactions, ICMMI 2015",
address = "Germany",
}