@Note: A workbench for Biomedical Text Mining

Abstract

Biomedical Text Mining (BioTM) is providing valuable approaches to the automated curation of scientific literature. However, most efforts have addressed the benchmarking of new algorithms rather than user operational needs. Bridging the gap between BioTM researchers and biologists' needs is crucial to solve real-world problems and promote further research. We present @Note, a platform for BioTM that aims at the effective translation of the advances between three distinct classes of users: biologists, text miners and software developers. Its main functional contributions are the ability to process abstracts and full-texts; an information retrieval module enabling PubMed search and journal crawling; a pre-processing module with PDF-to-text conversion, tokenisation and stopword removal; a semantic annotation schema; a lexicon-based annotator; a user-friendly annotation view that allows to correct annotations and a Text Mining Module supporting dataset preparation and algorithm evaluation. @Note improves the interoperability, modularity and flexibility when integrating in-home and open-source third-party components. Its component-based architecture allows the rapid development of new applications, emphasizing the principles of transparency and simplicity of use. Although it is still on-going, it has already allowed the development of applications that are currently being used.

The Artificial Intelligence Workbench: a retrospective review

“…In this section, we cover two complementary AIBench-based applications that also deal with biomedical texts, but allowing more advanced analyses based in text mining and text classification techniques: @Note and BioClass. @Note 10 is a biomedical text mining platform that copes with major information retrieval and extraction tasks and promotes multi-disciplinary research [Lourenço et al, 2009]. The use of AIBench allowed the authors to accomplish their design principles for @Note: interoperability, flexibility and modularity.…”

A Text Mining Approach for the Extraction of Kinetic Information from Literature

“…The framework is implemented over the AI-Bench framework, thus following the Model-View-Controller (MVC) paradigm [11]. @Note2 is organized into three main functional modules (Fig.…”

“…Different IE processes can be applied to a corpus, using some of the resources, to identify and extract bio-entities and their relationships. The Corpus processes sub-module contains three main processes: the NER process pool contains the Lexical resources and Linnaeus tagger [9], a hybrid dictionary and rule-based algorithm, the rulebased Chemistry tagger and the Machine Learning based ABNER tagger; the RE process pool contains a co-occurrence extraction process, a linguistic-based algorithm (Rel@tion) and a Machine learning approach; the Curator process allows to add/edit/remove entities and relations from IE results and to start a manual curation process [11].…”

“…The main goal of this work is the development of a BioTM pipeline for the automatic identification and collection of kinetic data from literature, implemented as the KineticRE plug-in for the framework @Note2 [11]. It works over annotated documents that result from an NER process.…”

Development and application of a keyword-based knowledge map for effective R&D planning

“…Furthermore, a method to extract data from a web page in HTML has been studied in the web-based environment (Hammer et al 1997) and online forums hotspot detection and forecast using text mining approaches are conducted by automatically analyzing the emotional polarity of a text (Li and Wu 2010). The technique is applied to not only database management and the Web environment but also foresight exercises and the automated curation of scientific literature through biomedical text mining (Santo et al 2006;Lourenco et al 2009). …”