Meta-evaluation of comparability metrics using parallel corpora
This work addresses the need for systematic evaluation of comparability metrics, which is crucial for applications like training Statistical MT systems in specialized domains, but it is incremental as it builds on existing metric evaluation approaches.
The authors tackled the problem of evaluating metrics for measuring corpus comparability by proposing a meta-evaluation method that calculates monolingual comparability scores on parallel corpora and correlates them using Pearson's r coefficient, with results showing consistent reliability across different datasets.
Metrics for measuring the comparability of corpora or texts need to be developed and evaluated systematically. Applications based on a corpus, such as training Statistical MT systems in specialised narrow domains, require finding a reasonable balance between the size of the corpus and its consistency, with controlled and benchmarked levels of comparability for any newly added sections. In this article we propose a method that can meta-evaluate comparability metrics by calculating monolingual comparability scores separately on the 'source' and 'target' sides of parallel corpora. The range of scores on the source side is then correlated (using Pearson's r coefficient) with the range of 'target' scores; the higher the correlation - the more reliable is the metric. The intuition is that a good metric should yield the same distance between different domains in different languages. Our method gives consistent results for the same metrics on different data sets, which indicates that it is reliable and can be used for metric comparison or for optimising settings of parametrised metrics.