The modelling of natural language tasks using data-driven methods is often hindered by the problem of insufficient naturally occurring examples of certain linguistic constructs. The task we address in this paper - quality estimation (QE) of machine translation - suffers from lack of negative examples at training time, i.e., examples of low quality translation. We propose various ways to artificially generate examples of translations containing errors and evaluate the influence of these examples on the performance of QE models both at sentence and word levels.
展开▼
