It uses the state to recombine hypotheses, discarding the worse scoring hypo where 2 have the same states. http://www.statmt.org/moses/?n=Moses.Background It doesn't have anything to do with search-algorithm
On 4 April 2014 16:14, David Mrva <[email protected]> wrote: > > >> end of the hypothesis. > > Your LM state is dependent on the entire target phrase? ie. these > > target phrases have difference states: > > a b c d e f g h i j > > z b c d e f g h i j > > This would probably negatively impact search as the stacks will have > > to be pruned more often, leading to search errors. > > > > I think this is also the experience of people trying to add syntactic > > LM to SMT decoders > > Hi Hieu, > > How does moses use the LM state? If I used the same state for both > phrases in your example and different LM scores, would moses keep both > hypotheses in its search space immediately after appending your two > phrases or would it discard one of them? Is this behaviour dependant on > the choice of the search-algorithm? > > David > > >> And when a hypothesis is being extended, its LM > >> state is extended by one target word at a time in a loop over the new > >> phrase from start to finish. Ngram LM implementation does not work in > >> this way and it seems to harm ngram performance. Can anyone shed some > >> light on the motivation behind the behaviour described above in > >> points 1-3? > >> > >> I used moses with its default, a.k.a. "normal", search algorithm (no > >> [search-algorithm] variable specified in my config). For completeness, > >> my config when using moses with its Kenlm class is pasted below. > >> > >> Best regards, > >> David > >> > >> > >> # input factors > >> [input-factors] > >> 0 > >> > >> # mapping steps > >> [mapping] > >> 0 T 0 > >> > >> [distortion-limit] > >> 6 > >> > >> # feature functions > >> [feature] > >> UnknownWordPenalty > >> WordPenalty > >> PhrasePenalty > >> PhraseDictionaryMemory name=TranslationModel0 table-limit=20 > >> num-features=4 path=model/phrase-table.1.gz input-factor=0 > >> output-factor=0 > >> LexicalReordering name=LexicalReordering0 num-features=6 > >> type=wbe-msd-bidirectional-fe-allff input-factor=0 output-factor=0 > >> path=model/reordering-table.1.wbe-msd-bidirectional-fe.gz > >> Distortion > >> KENLM lazyken=1 name=LM0 factor=0 path=lm/europarl.binlm.1 order=5 > >> > >> # dense weights for feature functions > >> [weight] > >> UnknownWordPenalty0= 1 > >> WordPenalty0= -1 > >> PhrasePenalty0= 0.2 > >> TranslationModel0= 0.2 0.2 0.2 0.2 > >> LexicalReordering0= 0.3 0.3 0.3 0.3 0.3 0.3 > >> Distortion0= 0.3 > >> LM0= 0.5 > >> > >> > >> > >> _______________________________________________ > >> Moses-support mailing list > >> [email protected] > >> http://mailman.mit.edu/mailman/listinfo/moses-support > >> > > > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support > -- Hieu Hoang Research Associate University of Edinburgh http://www.hoang.co.uk/hieu
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
