Exploiting Hidden Meanings: Using Bilingual Text for Monolingual Annotation

Abstract

The last decade has taught computational linguists that high performance on broad-coverage natural language processing tasks is best obtained using supervised learning techniques, which require annotation of large quantities of training data. But annotated text is hard to obtain. Some have emphasized making the most out of limited amounts of annotation. Others have argued that we should focus on simpler learning algorithms and find ways to exploit much larger quantities of text, though those efforts have tended to focus on linguistically shallow problems. In this paper, I describe my efforts to exploit larger quantities of data while still focusing on linguistically deeper problems such as parsing and word sense disambiguation. The trick, I argue, is to take advantage of the shared meaning hidden between the lines of sentences in parallel translation.