Skip to search boxSkip to navigationSkip to main content

Tunable Distortion Limits and Corpus Cleaning for SMT

  • Uppsala University
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
 Peer-review

Open access

Publication Information

Output type

Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
 Peer-review

Original language

English

Publication milestones

  • Published - 09/08/2013

Publication status

Published - 09/08/2013

ISBN (Print)

978-1-937284-57-2

Publication IDs

  • ORCID: /0000-0002-6103-7275/work/106363225

Host publication title

Proceedings of the Eighth Workshop on Statistical Machine Translation

Abstract

We describe the Uppsala University system for WMT13, for English-to-German translation. We use the Docent decoder, a local search decoder that translates at the document level. We add tunable distortion limits, that is, soft constraints on the maximum distortion allowed, to Docent. We also investigate cleaning of the noisy Common Crawl corpus. We show that we can use alignment-based filtering for cleaning with good results. Finally we investigate effects of corpus selection for recasing.

Access to documents