From 17c93d66db577f067e279036cebee6906bf633e3 Mon Sep 17 00:00:00 2001 From: Adam Weinberger Date: Tue, 8 Jul 2003 01:16:27 +0000 Subject: [PATCH] Add p5-WordNet-Similarity. This package consists of Perl modules along with supporting Perl programs that implement the semantic relatedness measures described by Leacock Chodorow (1998), Jiang Conrath (1997), Resnik (1995), Lin (1998), Hirst St Onge (1998) and the adapted gloss overlap measure by Banerjee and Pedersen (2002). The Perl modules are designed as object classes with methods that take as input two word senses. The semantic relatedness of these word senses is returned by these methods. A quantitative measure of the degree to which two word senses are related has wide ranging applications in numerous areas, such as word sense disambiguation, information retrieval, etc. For example, in order to determine which sense of a given word is being used in a particular context, the sense having the highest relatedness with its context word senses is most likely to be the sense being used. Similarly, in information retrieval, retrieving documents containing highly related concepts are more likely to have higher precision and recall values. A command line interface to these modules is also present in the package. The simple, user-friendly interface returns the relatedness measure of two given words. A number of switches and options have been provided to modify the output and enhance it with trace information and other useful output. Details of the usage are provided in other sections of this README. Supporting utilities for generating information content files from various corpora are also available in the package. The information content files are required by three of the measures for computing the relatedness of concepts. --- textproc/Makefile | 1 + textproc/p5-WordNet-Similarity/Makefile | 39 ++++++++++++++++++++++++ textproc/p5-WordNet-Similarity/distinfo | 1 + textproc/p5-WordNet-Similarity/pkg-descr | 27 ++++++++++++++++ textproc/p5-WordNet-Similarity/pkg-plist | 30 ++++++++++++++++++ 5 files changed, 98 insertions(+) create mode 100644 textproc/p5-WordNet-Similarity/Makefile create mode 100644 textproc/p5-WordNet-Similarity/distinfo create mode 100644 textproc/p5-WordNet-Similarity/pkg-descr create mode 100644 textproc/p5-WordNet-Similarity/pkg-plist diff --git a/textproc/Makefile b/textproc/Makefile index 9b0070e4a8af..4ef1891a25d2 100644 --- a/textproc/Makefile +++ b/textproc/Makefile @@ -253,6 +253,7 @@ SUBDIR += p5-URI-Find SUBDIR += p5-WDDX SUBDIR += p5-WordNet-QueryData + SUBDIR += p5-WordNet-Similarity SUBDIR += p5-XML-Catalog SUBDIR += p5-XML-DBMS SUBDIR += p5-XML-DOM diff --git a/textproc/p5-WordNet-Similarity/Makefile b/textproc/p5-WordNet-Similarity/Makefile new file mode 100644 index 000000000000..5871394389d4 --- /dev/null +++ b/textproc/p5-WordNet-Similarity/Makefile @@ -0,0 +1,39 @@ +# New ports collection makefile for: p5-WordNet-Similarity +# Date created: 07 July 2003 +# Whom: Adam Weinberger +# +# $FreeBSD$ +# + +PORTNAME= WordNet-Similarity +PORTVERSION= 0.05 +CATEGORIES= textproc perl5 +MASTER_SITES= ${MASTER_SITE_PERL_CPAN} +MASTER_SITE_SUBDIR= WordNet +PKGNAMEPREFIX= p5- + +MAINTAINER= ports@FreeBSD.org +COMMENT= Modules and a CLI to determine semantic relatedness using the WordNet database + +BUILD_DEPENDS= ${SITE_PERL}/WordNet/QueryData.pm:${PORTSDIR}/textproc/p5-WordNet-QueryData +RUN_DEPENDS= ${BUILD_DEPENDS} + +WNHOME?= ${LOCALBASE}/share/WordNet-1.7.1 + +PERL_CONFIGURE= yes +CONFIGURE_ENV= WNHOME=${WNHOME} +USE_REINPLACE= yes + +MAN3= WordNet::Similarity.3 WordNet::Similarity::jcn.3 \ + WordNet::Similarity::hso.3 WordNet::Similarity::vector.3 \ + WordNet::Similarity::random.3 WordNet::Similarity::res.3 \ + WordNet::Similarity::lesk.3 WordNet::Similarity::edge.3 \ + WordNet::Similarity::lin.3 WordNet::Similarity::lch.3 +post-patch: + @${REINPLACE_CMD} -e \ + '/wnUnixPath/s|/usr/local/WordNet-1.7.1|${WNHOME}|; \ + /wnUnixPath/s|."/dict"||' ${WRKSRC}/Makefile.PL + @${FIND} ${WRKSRC}/utils -type f| ${XARGS} ${REINPLACE_CMD} -e \ + 's|/usr/local/bin/perl|${PERL}|' + +.include diff --git a/textproc/p5-WordNet-Similarity/distinfo b/textproc/p5-WordNet-Similarity/distinfo new file mode 100644 index 000000000000..781e352920f6 --- /dev/null +++ b/textproc/p5-WordNet-Similarity/distinfo @@ -0,0 +1 @@ +MD5 (WordNet-Similarity-0.05.tar.gz) = dc82c6c971a480f3a082f6d9f1233d4a diff --git a/textproc/p5-WordNet-Similarity/pkg-descr b/textproc/p5-WordNet-Similarity/pkg-descr new file mode 100644 index 000000000000..f58ec498b7c7 --- /dev/null +++ b/textproc/p5-WordNet-Similarity/pkg-descr @@ -0,0 +1,27 @@ +From the README: + +This package consists of Perl modules along with supporting Perl programs that +implement the semantic relatedness measures described by Leacock Chodorow +(1998), Jiang Conrath (1997), Resnik (1995), Lin (1998), Hirst St Onge (1998) +and the adapted gloss overlap measure by Banerjee and Pedersen (2002). The Perl +modules are designed as object classes with methods that take as input two word +senses. The semantic relatedness of these word senses is returned by these +methods. A quantitative measure of the degree to which two word senses are +related has wide ranging applications in numerous areas, such as word sense +disambiguation, information retrieval, etc. For example, in order to determine +which sense of a given word is being used in a particular context, the sense +having the highest relatedness with its context word senses is most likely to +be the sense being used. Similarly, in information retrieval, retrieving +documents containing highly related concepts are more likely to have higher +precision and recall values. + +A command line interface to these modules is also present in the package. The +simple, user-friendly interface returns the relatedness measure of two given +words. A number of switches and options have been provided to modify the output +and enhance it with trace information and other useful output. Details of the +usage are provided in other sections of this README. Supporting utilities for +generating information content files from various corpora are also available in +the package. The information content files are required by three of the +measures for computing the relatedness of concepts. + +WWW: http://search.cpan.org/dist/WordNet-Similarity/ diff --git a/textproc/p5-WordNet-Similarity/pkg-plist b/textproc/p5-WordNet-Similarity/pkg-plist new file mode 100644 index 000000000000..75e38e32d7a0 --- /dev/null +++ b/textproc/p5-WordNet-Similarity/pkg-plist @@ -0,0 +1,30 @@ +bin/semCor17Freq.pl +bin/brownFreq.pl +bin/rawtextFreq.pl +bin/BNCFreq.pl +bin/semTagFreq.pl +bin/similarity.pl +bin/wordVectors.pl +bin/treebankFreq.pl +bin/compounds.pl +%%SITE_PERL%%/dbInterface.pm +%%SITE_PERL%%/get_wn_info.pm +%%SITE_PERL%%/stem.pm +%%SITE_PERL%%/string_compare.pm +%%SITE_PERL%%/WordNet/Similarity.pm +%%SITE_PERL%%/WordNet/infocontent.dat +%%SITE_PERL%%/WordNet/relation.dat +%%SITE_PERL%%/WordNet/Similarity/edge.pm +%%SITE_PERL%%/WordNet/Similarity/hso.pm +%%SITE_PERL%%/WordNet/Similarity/random.pm +%%SITE_PERL%%/WordNet/Similarity/lesk.pm +%%SITE_PERL%%/WordNet/Similarity/lin.pm +%%SITE_PERL%%/WordNet/Similarity/jcn.pm +%%SITE_PERL%%/WordNet/Similarity/lch.pm +%%SITE_PERL%%/WordNet/Similarity/res.pm +%%SITE_PERL%%/WordNet/Similarity/vector.pm +%%SITE_PERL%%/%%PERL_ARCH%%/auto/WordNet/Similarity/.packlist +@unexec rmdir %D/%%SITE_PERL%%/%%PERL_ARCH%%/auto/WordNet/Similarity 2>/dev/null || true +@unexec rmdir %D/%%SITE_PERL%%/%%PERL_ARCH%%/auto/WordNet 2>/dev/null || true +@unexec rmdir %D/%%SITE_PERL%%/%%PERL_ARCH%%/WordNet/Similarity 2>/dev/null || true +@unexec rmdir %D/%%SITE_PERL%%/%%PERL_ARCH%%/WordNet 2>/dev/null || true