Edited by Didier Bourigault, Christian Jacquemin and Marie-Claude L'Homme
[Natural Language Processing 2] 2001
► pp. 225–244
Many problems in terminology translation can be solved by working with existing translated texts. However, large-scale bilingual lexicon building from previously translated documents takes a lot of human effort. This chapter describes an automatic terminology alignment algorithm that can be used as a valuable pre-processing step in the interactive process of lexicon construction. The system can present the human expert with a summary of the plausible translations of high enough quality that it can reduce the number of sentences which need to be read by roughly a factor of five in many cases. When compared to a manually constructed lexicon in a particular case study, the automatic system achieved a precision of 56% and an exact recall of 70%. In addition, more than half the remaining terms can be obtained with minimal edit operations on the extracted text.
This list is based on CrossRef data as of 10 june 2024. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.