... aspects of translation quality. For example, while BLEU (Papineni et al., 2002)focuses on word- based n-gram precision, METEOR(Lavie and Agarwal, 2007) allows for stem/synonymmatching and incorporates ... MK(h)]. For exam-ple, suppose K = 2, M1(h) computes the BLEUscore, and M2(h) gives the METEOR score of h.Figure 1 illustrates the set of vectors {M (h)} in a10-best list. For two hypotheses ... recording the set of hypothesesthat maximizeskpkMk(h). For 0.6 < p1≤ 1 weget h = (0.9, 0.1), for p1= 0.6 we get (0.7, 0.6),and for 0 < p1< 0.6 we get (0.4, 0.8). At nosetting...