Title :
Measuring the impact of cognates in parallel text alignment
Author :
Bilbao, V. M Darriba ; Lopes, J. G Pereira ; Ildefonso, T.
Author_Institution :
Dept. de Informatica, Univ. de Vigo, Orense
Abstract :
This paper evaluates the impact of considering cognates for aligning parallel texts using our aligner. By considering that two words may be cognates if their similarity is higher than a certain threshold and if they are automatically selected as aligners, we tested different degrees of cognativeness, by varying threshold values. A new methodology to measure the quality of resulting alignments is presented. Two language pairs are addressed: Portuguese-Spanish, and Portuguese-English
Keywords :
language translation; natural language processing; text analysis; Portuguese-English languages; Portuguese-Spanish languages; machine translation; parallel text alignment; threshold values; Automatic testing; Data mining; Databases; Documentation; Error analysis; Humans; Information retrieval; Speech recognition; White spaces; Machine translation; Parallel text alignment; cognates; evaluation;
Conference_Titel :
Artificial intelligence, 2005. epia 2005. portuguese conference on
Conference_Location :
Covilha
Print_ISBN :
0-7803-9366-X
Electronic_ISBN :
0-7803-9366-X
DOI :
10.1109/EPIA.2005.341306
