Hi,

"other" is "discontinuous".

-phi

On Mon, Mar 21, 2011 at 11:20 AM, Neda NoorMohammadi
<[email protected]> wrote:
> Thanks for your answers.
>
> I need to understand the lexicalized reordering in moses which can
> change the code later.
> I have some questions:
>
> One of the intermediate  files which is made in model directory is
> “extract.o.sorted”, that includes reordering examples with its
> orientation.
> Why is not discontinues orientation in this file while In the
> documentation of moses is : there are  three orientations for a phrase
> pair(mono,swap,disc.)?
> For example, please consider these two samples for a same phrase pair
> (part of extract.o.sorted file):
>
> e1 e2 ||| mono mono ||| f1 f2
> e1 e2 ||| other mono ||| f1 f2
>
> What is the meaning of these samples?
> meanwhile, lexicalized reordering type is msd-fe.
>
>
>
> On 3/20/11, Philipp Koehn <[email protected]> wrote:
>> Hi,
>>
>> the best way to understand reordering, you have to keep
>> in mind the alignment to the source.
>>
>> If f1, f2, and f3, are the source phrases of the sentence in
>> that order, and you translate f1->e1, f3->e2, f2->e3,
>> meaning you first translate f1, then f3, and then f2, then
>> f1->e1 is consider monotone,
>> f3->e2 discontinuous (because it has connection to the previous phrase), and
>> f2->e3 a swap (because it swaps order with the previous phrase).
>>
>> The IWSLT paper gives some illustration of it,
>> I hope this helps.
>>
>> -phi
>>
>>
>>
>>> On 19/03/2011 15:05, Neda NoorMohammadi wrote:
>>>
>>> Hi,
>>>
>>>  The documentation is particularly scarce on lexicalized  reordering ,
>>> so I don’t understand the detail! Also, i studied Koehn’s IWSLT paper.
>>> How is lexicalized reordering in moses?
>>>
>>> Whether the reordering in moses just is done on segments of source
>>> sentence?  if so, when a segment for translating is selected, one of
>>> the hypothesis that is produced is:
>>> with considering  the probability of swap orientation  this phrase
>>> with previous phrase, the translation of this phrase with translation
>>> of previous phrase in old hypothesis is swapped and is build a new
>>> hypothesis. A simple sample is:
>>>
>>> e1 e2 e3 : old hypothesis
>>> e4: the translation of new segment
>>> (e3,e4) --> swap
>>> e1 e2 e4 e3: new hypothesis
>>>
>>> is it correct?
>>>
>>> Also, what is subcategory of lexicalized reordering code in moses?
>>>
>>> Thanks.
>>>
>>> _______________________________________________
>>> 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
>>
>
>
> --
> NoorMohammadi
>
> _______________________________________________
> 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

Reply via email to