A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is
Proceedings of the 18th conference on Computational linguistics -
This paper describes a method for retrieving patterns of words and expressions frequently used in a specic domain and building a dictionary for machine translation(MT). The method uses an untagged text corpus in retrieving word sequences and simplied part-of-speech templates in identifying their syntactic categories. The paper presents experimental results for applying the words and expressions to a patternbased machine translation system.doi:10.3115/992730.992759 fatcat:723gmbik4ncr7jhzxx7aoqikpy