It measures Precision, Recall, AER, and F_measurs metrics to evaluate the quality of word alignment.
evaluation(file.gold = 'gold.RData',
file.align = 'alignment.-1.3.RData',
agn = c('my.agn','an.agn'), alpha = 0.3)the gold standarad file name.
the alignment file name.
character string including two values. If "my.agn", the user wants to evaluate one-to-many word alignment using the align.ibm1 function in this package. If "an.agn", the user wants to evaluate word alignment results which are obtained by another software.
is a parameter that sets the trade-off between Precision and Recall.
A list.
A decimal number.
A decimal number.
A decimal number.
A decimal number.
A decimal number.
To evaluate word alignment quality, we need to a "reference alignment" (a gold standard for the word alignment) of a test set.
In order to read the gold into RData format and to compare it with the word alignment results, the gold standard file name must be set in file.gold.
Fraser F., Marcu D. (2007), "MeasuringWord Alignment Quality for Statistical Machine Translation.", Computational Linguistics, 33(3), 293-303.
Koehn P. (2010), "Statistical Machine Translation.", Cambridge University, New York.
Och F., Ney H.(2003)."A Systematic Comparison Of Various Statistical Alignment Models.", 2003 Association for Computational Linguistics, J03-1002, 29(1).
Wang X. "Evaluation of Two Word Alignment Systems.", Final Thesis, Department of Computer and Information Science.