Word Clustering Approach to Bilingual Document Alignment (WMT 2016 Shared Task)

Abstract

Our participation in Bilingual Document Alignment shared task at WMT16 focuses on building a language-independent, scalable system for aligning documents based on content as opposed to using webpage meta information. The resulting system is capable of producing scored n-best lists of candidate pages and can therefore be adapted to tasks where either precision or recall is maximized. We conduct a series of experiments that show the effectiveness of the system without any specific tuning.