ABNER 1.5

ABNER is a software tool for molecular biology text analysis. It began as a user-friendly interface for a system developed as part of the NLPBA/BioNLP 2004 Shared Task challenge. The details of that system are described in the paper below (Settles, 2004).<br /><br />At ABNER's core is a statistical machine learning system using linear-chain conditional random fields (CRFs) with a variety of orthographic and contextual features. Version 1.5 includes two models trained on the NLPBA and BioCreative corpora, for which performance is roughly state of the art (F1 scores of 70.5 and 69.9 respectively; details here). The new version also includes a Java API allowing users to incorporate ABNER into their systems, as well as train and use models for other data. Here's a pretty screenshot:<br />[ABNER screenshot]<br />Features.<br /><br /> * Simultaneously recognize multiple named entities (2 trained models included).<br /> * Intuitive, interactive user interface.<br /> * Optional built-in tokenization and sentence segmentation algorithms, robust to wrapped lines and biomedical abbreviations.<br /> * Open text files and save annotations (SGML, IOB, and ABNER formats supported).<br /> * Directory-recursive batch annotation of text files.<br /> * Java API to incorporate ABNER into customized biomedical text applications.<br /> * API includes routines for training ABNER on new corpora

Requirements:	No special requirements
Platforms:	Mac, Mac OSX
Keyword:	Abner,  Biomedical,  Corpora,  Details,  Entities,  Files,  Included,  Includes,  Incorporate,  Interface,  Models,  Multiple,  Named,  Recognize,  Screenshotfeatures,  System,  Systems,  Train,  Trained
Users rating:	0/10