Hello Camelia, Thanks for pointing towards your thesis. However there are 2 main things I wanted to try differently. I want to do triangulation at decoding time and not sentence translation strategy. Thanks again.
Sent from Samsung Mobile -------- Original message -------- From: Camelia Ignat <[email protected]> Date: 26/10/2014 06:29 (GMT+09:00) To: [email protected],prajdabre <[email protected]> Subject: Re: Phrase pair generation at run time using Source-Pivot and Pivot-Target phrase tables Hi, In my PhD thesis (defended in 2009) I have studied different ways to introduce a pivot language in the alignment and translation models: at phrase-table level, at alignment level, and at the decoding time. The methods and the experiments are described in chapter 6 and 7. See the thesis here: https://sites.google.com/site/cameliaignat/home/phd-thesis Even if it will not answer directly to your question, maybe it can help. Regards, camelia On 10/24/2014 04:44 PM, [email protected] wrote: > > 1. Re: Phrase pair generation at run time using Source-Pivot and > Pivot-Target phrase tables (prajdabre) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Fri, 24 Oct 2014 22:34:29 +0900 > From: prajdabre <[email protected]> > Subject: Re: [Moses-support] Phrase pair generation at run time using > Source-Pivot and Pivot-Target phrase tables > To: Barry Haddow <[email protected]> > Cc: [email protected] > Message-ID: <[email protected]> > Content-Type: text/plain; charset="utf-8" > > I will get the blowup but since its generating phrases for a sentence only it > can fit in memory. > Ofc the time would be more but im eager to see what happens. > > > Sent from Samsung Mobile > > -------- Original message -------- > From: Barry Haddow <[email protected]> > Date: 24/10/2014 20:09 (GMT+09:00) > To: Raj Dabre <[email protected]> > Cc: [email protected] > Subject: Re: [Moses-support] Phrase pair generation at run time using > Source-Pivot and Pivot-Target phrase tables > > On 24/10/14 11:06, Raj Dabre wrote: >> That is a good starting? point suggestion. >> Many thanks. >> >> Perhaps an easier option would be to do the synthesis offline. In >> other words, take your two tables and create a pivot table from them, >> and then use it like a normal phrase table. >> >> This I have been doing for 6 months but the phrase tables generated >> are super-huge where the size almost is a square of the original size. >> I end up having to keep a threshold frequency and kill potentially >> good phrase pairs. Thats why I want to generate it online and keep all >> the pairs. > But if you synthesise the phrase pairs inside the decoder, then won't > you get the same n^2 blow-up? I think you have to find a good way to > prune however you implement the synthesis. > > >> Thanks again. >> >> On Fri, Oct 24, 2014 at 6:58 PM, Barry Haddow >> <[email protected] <mailto:[email protected]>> wrote: >> >> ???? Hi Raj >> >> ???? You could create a custom phrase table implementation to produce >> ???? your synthesised phrase pairs. Have a look at the existing phrase >> ???? table implementations in moses/TranslationModel. In particular, >> ???? you need to subclass PhraseDictionary. The method >> ???? GetTargetPhraseCollectionLEGACY() returns a collection of phrase >> ???? pairs, given a source phrase. >> >> ???? Perhaps an easier option would be to do the synthesis offline. In >> ???? other words, take your two tables and create a pivot table from >> ???? them, and then use it like a normal phrase table. >> >> ???? cheers - Barry >> >> >> ???? On 21/10/14 11:14, Raj Dabre wrote: >> >> ???????? Hello, >> ???????? I am currently doing research on using pivot languages for >> ???????? Phrase based SMT. >> >> ???????? My current method involves the usage of alternate decoding >> ???????? paths feature to combine multiple synthesized Source-Target >> ???????? phrase tables. (I have noticed that not many people exploit >> ???????? this method or even if they do.... they don't mention it clearly). >> >> ???????? However pre-synthesized? phrase tables need to be pruned to >> ???????? remove low probability phrase pairs and I would like to >> ???????? generate phrase pairs via a pivot at run time. I am ok with >> ???????? taking additional decoding time. >> >> ???????? I am aware that Bertoldi (2008) had already mentioned that he >> ???????? had used this method but this is not present in the moses >> ???????? decoder release. >> ???????? I would very much like to implement this but do not know where >> ???????? to start. >> ???????? If someone could tell me the section of code that reads in >> ???????? phrase pairs given a source phrase I think I might be able to >> ???????? do something. >> ???????? Any help would be appreciated. >> >> ???????? Thanks in advance. >> >> ???????? -- >> ???????? Raj Dabre. >> ???????? Research Student, >> ???????? Graduate School of Informatics, >> ???????? Kyoto University. >> ???????? CSE MTech, IITB., 2011-2014 >> >> >> >> ???????? _______________________________________________ >> ???????? Moses-support mailing list >> ???????? [email protected] <mailto:[email protected]> >> ???????? http://mailman.mit.edu/mailman/listinfo/moses-support >> >> >> >> ???? -- >> ???? The University of Edinburgh is a charitable body, registered in >> ???? Scotland, with registration number SC005336. >> >> >> >> >> -- >> Raj Dabre. >> Research Student, >> Graduate School of Informatics, >> Kyoto University. >> CSE MTech, IITB., 2011-2014 >> >
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
