Abstract

Word alignment of parallel texts is typically carried out using many kinds of knowledge, or information sources, in concert, i.e., it is profitably viewed as a kind of cooperative process, where e.g. distribution, string similarity, cooccurrence statistics, and other information sources are used together. We investigate a novel such information source in this paper, namely the use of a third language as a `pivot' to increase alignment recall, hence the name pivot alignment. The results of the preliminary experiments reported here indicate that pivot alignment increases word alignment recall, without sacrificing precision.

Citations