Moses Support Digest:2.718 in the phrase-table
[Moses-support] 2.718 in the phrase-table
The exact purpose of the value 2.718 is what I am not sure of.As far as I know, the value is used for preferring the hypothesis with less phrases tothe one that use more phrases(words) for the same coverage of the source sentence duringthe prefix cost comparison inside priority queue( for the hyps that covers the same source range ).for example ) phrase_1 + phrase_2 + phrase_3 )to prefer hyp1 to hyp2 by multiplying hyp1 by 2.718.This is how I understand the use of the value, since longer phrase has empirically better translationthan the one made up of word-based translation.Is there any one who can confirm my belief, or to correct my conclusion?p.s. Is 2.718 the Euler’s number? If it is, why is the weight determined as such?
Re:[Moses-support] 2.718 in the phrase-table
The last weight from the phrase-table corresponds to the phrase penalty as explained in
http://www.statmt.org/moses/?n=FactoredTraining.ScorePhrases
This features benefits translations that use less units to decode.
It is the Euler’s number and it is determined as such because the decoder uses natural logarithms to add the weights, instead of multiplying probabilities. Hence, 2.718 will become 1 during decoding as a way of saying “I’m using yet another phrase unit to perform a translation”.
So you were quite right after all 
)
Re:[Moses-support] 2.718 in the phrase-table
Anecdotally, this feature also isn’t especially important, see e.g.:
http://www.mt-archive.info/AMTA-2006-Lopez.pdf
NOTICE:This is digested from the Moses-support mailing list, which supports for the moses SMT decoder.
Related posts:
- Moses Support Digest:Alignment information from binary phrase table
- Moses Support Digest:Reading binary phrase table from the disk
- Moses Support Digest: moses_chart and recaser phrase-table
- Moses Support Digest:Aligned phrase counts
- Moses Support Digest:CreateBerkeleyPt and On-Disk Rule Table
- Moses Support Digest: EMS table binarization
- Moses Support Digest: Regarding moses.weight-reused.ini
- Moses Support Digest: Moses seems to hang
- Moses Support Digest:ConfusionNet GetSubString error when using lattice with UTF8 input
- Moses Support Digest:POS translation