log prob score of the hypothesis (SMT global score)
log probability score of the hypothesis (SMT global score) normalised by source sentence length
size of nbest list (number of hypotheses generated)
using n-best for building an LM: sentence 1-gram log-probability
using n-best for building an LM: sentence 1-gram log-probability / sentence length
using n-best for building an LM: sentence 1-gram perplexity
using n-best for building an LM: sentence 2-gram log-probability
using n-best for building an LM: sentence 2-gram log-probability / sentence length
using n-best for building an LM: sentence 2-gram perplexity
using n-best for building an LM: sentence 3-gram log-probability
using n-best for building an LM: sentence 3-gram log-probability / sentence length
using n-best for building an LM: sentence 3-gram perplexity
Moses distortion feature 1
Moses distortion feature 2
Moses distortion feature 3
Moses distortion feature 4
Moses distortion feature 5
Moses distortion feature 6
Moses distortion feature 6
Moses phrase table feature 1
Moses phrase table feature 2
Moses phrase table feature 3
Moses phrase table feature 4
Moses phrase table feature 5
Moses word penalty feature
maximum size of the bi-phrases (number of words) in the translation 
proportion of unknown/untranslated words
average relative frequency of words in the translation across the nbest list
score-weighted average relative frequency of words in the translation across the n-best list 
average relative frequency of the words in the translation across the n-best list occurring in the same position as the target word
ratio of log prob (SMT global score) of the current hypothesis to the sum of the log prob score of all hypotheses in the n-best list
ratio of log prob (SMT global score) of the current hypothesis to the sum of the log prob score of all hypotheses in the n-best list
average size of hypotheses in the n-best list
n-best list density (vocabulary size / average sentence length)
fertility of the words in the source sentence compared to the n-best list in terms of words (vocabulary size / source sentence length)
edit distance of the current hypothesis to the center hypothesis (closest hypothesis to all others in the n-best list)
percentage of other hypothesis with and edit distance to the centre hypothesis < current hypothesis edit distance to the centre * 0.5
percentage of other hypothesis with and edit distance to the centre hypothesis < current hypothesis edit distance to the centre * 0.35
Moses search graph info: totalHypotheses
Moses search graph info: number of discarded search graph nodes
Moses search graph info: percentage of discarded graph nodes
Moses search graph info: number of pruned search graph nodes
Moses search graph info: proportion of pruned search graph nodes 
Moses search graph info: number of recombined graph nodes
Moses search graph info: proportion of recombined graph nodes
percentage of incorrectly translated possessive pronouns
percentage of incorrectly translated direct object personal pronouns