152017-03-17 14:01:14MaciejOgrodniczuk142013-02-01 11:03:43JakubWaszczuk132013-02-01 10:55:00JakubWaszczuk122013-02-01 10:43:44JakubWaszczuk112013-02-01 10:36:17JakubWaszczuk102013-02-01 10:25:57JakubWaszczuk92013-02-01 10:25:07JakubWaszczuk82013-02-01 10:16:08JakubWaszczuk72013-01-23 12:25:44MaciejOgrodniczuk62013-01-23 12:19:02MaciejOgrodniczuk52012-06-25 19:29:44BeataWojtowicz42012-06-19 10:41:22MichalLenart32012-06-19 10:41:13MichalLenart22012-05-14 09:49:49BeataWojtowicz12012-05-14 09:48:23BeataWojtowicz

Nerf is a statistical named entity recognition tool based on linear-chain conditional random fields. Principal developer: Jakub Waszczuk License: GPL v.3

See the README file from the development repository.

Nerf is available in a form of a software distribution which can be downloaded from Hackage using the Cabal tool. To compile Nerf you will also need the Glasgow Haskell Compiler (GHC). The simplest way to get both Cabal and GHC is to install the Haskell Platform. Please see the documentation for more information about the installation process.

A model for the Polish language has been trained on the manually annotated subcorpus of the National Corpus of Polish (NCP). An archive file with the model can be downloaded from here. The model can be used to recognize embedded structures of named entities consistent with the type hierarchy used in NCP.

The Python version of Nerf is no longer supported. Authors: Jakub Waszczuk, Michał Lenart License: GPL v.3 Readme file of the Python version, in English NERF.pdf You can download the obsolete distribution package from here. The package consists of three components: Python pycrf library, which has to be installed before the Nerf tool can be used, The Nerf tool itself, Supplementary data: trained models and examples of configuration files.