Paper: Sub-Sentential Alignment Using Substring Co-Occurrence Counts

ACL ID P06-3003
Title Sub-Sentential Alignment Using Substring Co-Occurrence Counts
Venue Annual Meeting of the Association of Computational Linguistics
Session Student Session
Year 2006
Authors
  • Fabien Cromierès (Institute of Information and Applied Mathematics Grenoble, Grenoble France)

In this paper, we will present an efficient method to compute the co-occurrence counts of any pair of substring in a paral- lel corpus, and an algorithm that make use of these counts to create sub- sentential alignments on such a corpus. This algorithm has the advantage of be- ing as general as possible regarding the segmentation of text.