diff options
author | Eric Bavier <bavier@member.fsf.org> | 2015-03-17 11:03:31 -0500 |
---|---|---|
committer | Eric Bavier <bavier@member.fsf.org> | 2015-03-17 13:03:50 -0500 |
commit | d7de088395e10ec0f35584afd50bc63b3a6d18c6 (patch) | |
tree | 6497e5042d433217e64b4953bafd8b3c7bdbed12 /gnu/packages | |
parent | 9766e4fef1745d46a0b0eb6bcf35b6f3653d09f2 (diff) | |
download | guix-d7de088395e10ec0f35584afd50bc63b3a6d18c6.tar guix-d7de088395e10ec0f35584afd50bc63b3a6d18c6.tar.gz |
gnu: Add Lingua-EN-Tagger.
* gnu/packages/language.scm (perl-lingua-en-tagger): New variable.
Diffstat (limited to 'gnu/packages')
-rw-r--r-- | gnu/packages/language.scm | 33 |
1 files changed, 32 insertions, 1 deletions
diff --git a/gnu/packages/language.scm b/gnu/packages/language.scm index fff651ba2e..2c080cc602 100644 --- a/gnu/packages/language.scm +++ b/gnu/packages/language.scm @@ -19,9 +19,10 @@ (define-module (gnu packages language) #:use-module (gnu packages) #:use-module (gnu packages perl) + #:use-module (gnu packages web) #:use-module (guix packages) #:use-module (guix build-system perl) - #:use-module ((guix licenses) #:select (gpl2)) + #:use-module ((guix licenses) #:select (gpl2 gpl3)) #:use-module (guix download)) (define-public perl-lingua-en-findnumber @@ -114,6 +115,36 @@ converting a word to singular or plural.") digits, is a cardinal or ordinal number.") (license (package-license perl)))) +(define-public perl-lingua-en-tagger + (package + (name "perl-lingua-en-tagger") + (version "0.24") + (source + (origin + (method url-fetch) + (uri (string-append "mirror://cpan/authors/id/A/AC/ACOBURN/" + "Lingua-EN-Tagger-" version ".tar.gz")) + (sha256 + (base32 + "0qksqh1zi8fz76a29s2ll4g6yr8y6agmzgq7ngccvgj3gza5q241")))) + (build-system perl-build-system) + (propagated-inputs + `(("perl-memoize-expirelru" ,perl-memoize-expirelru) + ("perl-lingua-stem" ,perl-lingua-stem) + ("perl-html-parser" ,perl-html-parser) + ("perl-html-tagset" ,perl-html-tagset))) + (home-page "http://search.cpan.org/dist/Lingua-EN-Tagger") + (synopsis "Part-of-speech tagger for English natural language processing") + (description "This module is a probability based, corpus-trained tagger +that assigns part-of-speech tags to English text based on a lookup dictionary +and a set of probability values. The tagger assigns appropriate tags based on +conditional probabilities - it examines the preceding tag to determine the +appropriate tag for the current word. Unknown words are classified according +to word morphology or can be set to be treated as nouns or other parts of +speech. The tagger also extracts as many nouns and noun phrases as it can, +using a set of regular expressions.") + (license gpl3))) + (define-public perl-lingua-en-words2nums (package (name "perl-lingua-en-words2nums") |