Title :
Leveraging multiple languages to improve statistical MT word alignments
Author :
Filali, Karim ; Bilmes, Jeff
Author_Institution :
Dept. of Comput. Sci. & Eng. & Electr. Eng., Washington Univ., Seattle, WA
Abstract :
We present a new multilingual statistical MT word alignment model based on a simple extension of the IBM and HMM models and a two-step alignment procedure. Preliminary results on a small hand-aligned subset of the Europarl corpus show a 7% relative improvement over a state of the art alignment model
Keywords :
hidden Markov models; language translation; natural languages; HMM models; hand-aligned subset; leveraging multiple languages; machine translation; statistical MT word alignments; Computer science; Hidden Markov models; Information resources; Mathematics; Natural languages; Optimized production technology; Redundancy; Robustness;
Conference_Titel :
Automatic Speech Recognition and Understanding, 2005 IEEE Workshop on
Conference_Location :
San Juan
Print_ISBN :
0-7803-9478-X
Electronic_ISBN :
0-7803-9479-8
DOI :
10.1109/ASRU.2005.1566493
