On Some Pitfalls in Automatic Evaluation and Significance Testing for MT

We investigate some pitfalls regarding the discriminatory power of MT evaluation metrics and the accuracy of statistical significance tests. In a discriminative reranking experiment for phrase-based SMT we show that the NIST metric is more sensitive than BLEU or F-score despite their incorporation of aspects of fluency or meaning adequacy into MT evaluation. In an experimental comparison of two statistical significance tests we show that p-values are estimated more conservatively by approximate randomization than by bootstrap tests, thus increasing the likelihood of type-I error for the latter. We point out a pitfall of randomly assessing significance in multiple pairwise comparisons, and conclude with a recommendation to combine NIST with approximate randomization, at more stringent rejection levels than is currently standard.