For a given Sentence-Aligned Parallel Corpus, it aligns words for each sentence pair. It considers one-to-many and symmetrization alignments. Moreover, it evaluates the quality of word alignment based on this package and some other software. It also builds an automatic dictionary of two languages based on given parallel corpus.
|Author||Neda Daneshagr and Majid Sarmad.|
|Date of publication||2016-12-30 14:42:40|
|License||GPL (>= 2)|
align_test.set: Computing One-to-Many Word Alignment Using a Parallel Corpus...
cons.agn: Constructing Cross Tables of the Source Language Words vs the...
culf: Make a String's First n Characters Lowercase
Evaluation1: Evaluation of Word Alignment Quality
ExcelToR: Converting Excel Files Into Required R Format
mydictionary: Building an Automatic Bilingual Dictionary
prepareData: Initial Preparations of Bitext before the Word Alignment and...
squareN: Finding Neighborhood Locations
Symmetrization: Calculating Symmetric Word Alignment
word_alignIBM1: Computing One-to-Many Word Alignment Using IBM Model 1 for a...
word.alignment-package: Computing Word Alignment Using IBM Model 1 (and...