Using a Parallel Transcript/Subtitle Corpus for Sentence Compression

Abstract

In this paper we describe the collection of a parallel corpus (in Dutch) and its use in a sentence compression tool with the intention to automatically generate subtitles for the deaf from transcripts of a television program. First, the collection of the corpus is described, together with the manipulations and transformations performed on that corpus. Second, a hybrid sentence compression tool is described together with its evaluation.