Search results for "distribution:Lingua-Align Lingua::Alignment"
Lingua::Align::Words - Module for word alignment
This module essentially inherits everything from tree alignment but adds some tools which are specific to word alignment....
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align - Perl modules for the alignment of parallel corpora
Lingua::Align contains modules for automatic tree alignment based on discriminative classification and alignment inference. More details about the tree aligner can be found in Lingua::Align::Trees. The following gives a general overview and motivatio...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::Features - Feature extraction for tree alignment
Extract features from a pair of nodes from two given syntactic trees (source and target language). The trees should be complex hash structures as produced by Lingua::Align::Corpus::Treebank::TigerXML. The returned features are given as simple key-val...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::LinkSearch - Search algorithms for tree alignment
Class factory for searching the best tree alignment based on local link scores Various strategies have been implemented. Use the argument "-link_search" in the constructor to choose from the following search strategies: threshold .............. greed...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::LinkSearch::Src2Trg - Source-to-target alignment
This module implements an alignment strategy that greedily aligns the best scoring target tree node to each source tree node. Only one link per source tree node is allowed....
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::Trees - Perl modules implementing a discriminative tree aligner
This module implements a discriminative tree aligner based on binary classification. Alignment features are extracted for each candidate node pair to be used in a standard binary classifier. As a default we use a MaxEnt learner using a log-linerar co...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::LinkSearch::Trg2Src - Greedy target-to-source alignment
This module implements an alignment strategy that greedily aligns the best scoring source tree node to each target tree node. Only one link per target tree node is allowed....
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::Corpus::Parallel::WPT - Read data from the WPT word alignment task
TIEDEMANN/Lingua-Align-0.04
-
10 Dec 2012 18:31:24 UTC
Lingua::Align::Corpus::Parallel::Giza - Read the Viterbi word alignment produced by GIZA++
TIEDEMANN/Lingua-Align-0.04
-
10 Dec 2012 18:31:24 UTC
Lingua::Align::LinkSearch::Assignment - Alignment as an assignment problem in bipartite graphs
This module uses the Kuhn-Munkres algorithm using Algorithm::Munkres to assign links between tree nodes. In this way, alignment is treated as an assignment problem in a bipartite graph. As a consequence, only one-to-one alignments will be found. Well...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::LinkSearch::Intersection - Intersection between source-to-target and target-to-source alignment
This modules implements the intersection of Src2Trg and Trg2Src alignments....
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
treealign - training tree alignment classifiers and aligning syntactic trees
This script allows you to train a tree alignment model and to apply them to parallel treebanks. Tree alignment is based on local binary classification and rich feature sets. Currently, training data has to be in Stockholm Tree Aligner format. The out...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::LinkSearch::Greedy - Simple greedy search for links
This module implements a greedy best-first alignment strategy that allows one-to-one links only (competitive linking)....
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
coocfreq - count co-occurrence frequencies for arbitrary features of nodes in a parallel treebank
This script counts frequencies and co-occurrence frequencies of source and target language features. It runs through the sentence aligned treebank and combines all node pairs. Note that co-occurrence frequencies in a sentence are " max( srcfreq(srcfe...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
sta2moses - convert from Stockholm Tree Aligner format to Moses/GIZA++ (plain text)
This script reads through a parallel treebank using the tree alignment file (alignments.xml) and produces sentence aligned plain text files (to be used with Moses/Giza++). The corpus will be stored in alignments.src and alignments.trg....
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::LinkSearch::Src2TrgWellFormed - Source-to-target alignment with constraints
This module implements an alignment strategy that greedily aligns the best scoring target tree node to each source tree node. Only one link per source tree node is allowed. Wellformedness constraints are enforced. The option "-weal_wellformedness" re...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
Lingua::Align::LinkSearch::Cascaded - cascaded link search strategies
This module allows to combine several alignment inference strategies into a "cascade of linking steps". Use the constructor option '-link_search' to specify the steps to be taken. The syntax is (strategies separated by '-'): cascaded:strategy1-strate...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC
treealigneval - a script for computing precision and recall scores for tree aligmnent
Both gold-standard-file and tree-alignment-file should be in Stockholm Tree Aligner Format. Here is an example: <?xml version="1.0" ?> <treealign> <head> <alignment-metadata> <date>Tue May 4 16:23:04 2010</date> <author>Lingua-Align</author> </alignm...
TIEDEMANN/Lingua-Align-0.04 - 10 Dec 2012 18:31:24 UTC