Publications
Authors:
  • Lucia Specia , Zhuoran Wang , Marco Turchi , John Shawe-Taylor , Craig Saunders
Citation:
MT Summit 2009 (Machine Translation Summit XII), Ottawa, Ontario, Canada, August 26-30, 2009. Full paper available <a href=http://eprints.pascal-network.org/archive/00005490/01/MTS-2009-Specia.pdf> here</a>
Abstract:
We investigate the problem of estimating the quality of the output of machine translation systems at the sentence level when reference translations are not available. The focus is on automatically identifying a threshold to map
a continuous predicted score into ?good?/?bad? categories for filtering out bad-quality cases in a translation post-edition task. We use the theory of Inductive Confidence Machines (ICM) to identify this threshold according to a
confidence level that is expected for a given task. Experiments show that this approach gives improved estimates when compared to those based on classification or regression algorithms without ICM.
Year:
2009
Report number:
2009/034