Hi, I'm also curious about max-phrase-lenght.
On a separate note: what would go wrong if you cut the partial input you are providing down to just the last N-1 words, where N is the maximum order of your language models? Which sparse features look this far? What would one need to supply to get their scores even without this full prefix? How far back would OSM look? Cheers, O. On December 4, 2015 5:28:00 PM CET, Philipp Koehn <[email protected]> wrote: >Hi, > >interesting... this may be due to the maximum phrase length (the XML >specified translation is treated as a phrase translation), which is 20 >by default. > >You can tell the decoder otherwise with the switch -max-phrase-length. > >I'd be interested to know, if this fixes the problem. > >-phi > >On Wed, Dec 2, 2015 at 9:30 PM, He He <[email protected]> wrote: >> Hi, >> >> Yes. The input to the decoder is " -v 0 -threads 4 -n-best-list - 10 >> --print-alignment-info-in-n-best -xml-input exclusive >> >> If I break the long translation into parts it works though. >> >> He >> >> On Wed, Dec 2, 2015 at 6:14 PM, Philipp Koehn <[email protected]> wrote: >>> >>> Hi, >>> >>> it's not clear to me what you are exactly specifying to the decoder, >>> but what you intend to do should work. >>> >>> Did you use the switch "-xml-input exclusive"? >>> What exactly do you specify as input? >>> >>> -phi >>> >>> >>> >>> >>> >>> On Tue, Nov 24, 2015 at 10:19 PM, He He <[email protected]> wrote: >>> > Hi there, >>> > >>> > I'm trying to do translation conditioned on some already >translated >>> > prefix >>> > (essentially what -continue-partial-translation was supposed to >do). I'm >>> > using -xml-input exclusive to pass in the prefix source and >translation. >>> > >>> > However, when the prefix becomes long, this doesn't work, e.g. >>> > <p translation="Britain 's trade house E D & F Man said on the >amount of >>> > money in eastern europe , sugar beet output both Ukraine and >Russia in"> >>> > 英国 >>> > の ED & F マン 社 に よる と , 96 / 97 年度 の 東欧 の ビート 生産 は , ウクライナ やロシア の >生産 減少 >>> > により</p> 大幅 な 低下 が 予想 さ れ , 厳しい もの に なる> 0 ||| 英国 の ED & F英国 の ED & >F マン >>> > 社 に >>> > よる と / 96 , 97 年度 の 東欧 の ビート 生産 は ウクライナ , や ロシア の 生産 減少 により >substantial >>> > decline was expeted to be tough ||| LexicalReordering0= -4.48185 >>> > -7.01678 >>> > -1.48808 -4.3759 -6.89465-0.942918 Distortion0= -12 LM0= -227.918 >>> > WordPenalty0= -40 PhrasePenalty0= 36 TransltionModel0= -7.25771 >-34.5474 >>> > -2.80336 -22.3651 ||| -3322.64" >>> > >>> > It just copies the source prefix. I suspect it's because many >words now >>> > becomes UNK due to ignoring entries in phrase table that overlaps >the >>> > prefix. >>> > >>> > Is there a way around this? Thanks a lot in advance! >>> > >>> > Best, >>> > He >>> > >>> > _______________________________________________ >>> > 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 >> > >_______________________________________________ >Moses-support mailing list >[email protected] >http://mailman.mit.edu/mailman/listinfo/moses-support -- Ondrej Bojar (mailto:[email protected] / [email protected]) http://www.cuni.cz/~obo _______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
