Thanks a bunch.

John

On Wed, Nov 11, 2009 at 1:02 PM, Philipp Koehn <[email protected]> wrote:
> Hi John,
>
> the answer is extract.cpp (I had to look it up myself).
>
> The orientation decision is handled based on alignment points as described
> in the tutorial slide:
>
>    // orientation to previous E
>    bool connectedLeftTop  = isAligned( sentence, startF-1, startE-1 );
>    bool connectedRightTop = isAligned( sentence, endF+1,   startE-1 );
>
> So what happens when startF == 0, so we are looking up
> alignments for alignment points for word "-1"?
>
> Let's look at the isAligned function:
>
> bool isAligned ( SentenceAlignment &sentence, int fi, int ei ) {
>  if (ei == -1 && fi == -1) return true;
>  if (ei <= -1 || fi <= -1) return false;
>
> So, if the first target (E) phrase is in the top left corner (translated into
> the first source (F) phrase), it is monotone, but not otherwise.
>
> -phi
>
> On Wed, Nov 11, 2009 at 8:52 PM, John DeNero <[email protected]> wrote:
>> Hi Philipp & Chris,
>>
>> Thanks for the help so far.  One more question about a special case:
>> What is the reordering of the first source phrase with regard to the
>> previous phrase? Always mono?  (Another reasonable policy might be
>> mono if aligned to the first target phrase and discontinuous
>> otherwise.)  Does the last source phrase with regard to the following
>> context have the same policy?  If you don't know off the top of your
>> head, I'll dig into the data and figure it out.
>>
>> Thanks,
>> John
>>
>> On Wed, Nov 11, 2009 at 11:59 AM, Philipp Koehn <[email protected]> wrote:
>>> Hi,
>>>
>>> the determination in training, whether a phrase is swap (with regard to 
>>> previous
>>> phrase or next) is based on alignment points around the phrase.
>>>
>>> Slide 112 in this tutorial defines which alignment points are looked at:
>>> http://www.iccs.inf.ed.ac.uk/~pkoehn/publications/tutorial2006.pdf
>>>
>>> So, yes, swap swap is possible - it happens if a sequence of
>>> phrases is in inverse order.
>>>
>>> -phi
>>>
>>> On Wed, Nov 11, 2009 at 7:49 PM, John DeNero <[email protected]> wrote:
>>>> Thanks, Chris.  Just to clarify, am I interpreting the following cases
>>>> correctly, where P is the phrase pair in question and X are word
>>>> alignments in neighboring corners, and the source goes left to right?
>>>>
>>>> The "mono swap" case:
>>>> $ zcat extract.o.gz | grep "mono swap"  | wc -l
>>>> 41043
>>>>
>>>> X X
>>>>  P
>>>>
>>>> The "swap swap" case:
>>>> $ zcat extract.o.gz | grep "swap swap"  | wc -l
>>>> 61745
>>>>
>>>>  X
>>>>  P
>>>> X
>>>>
>>>>
>>>> The "swap mono" case:
>>>> $ zcat extract.o.gz | grep "swap mono"  | wc -l
>>>> 50403
>>>>
>>>>  P
>>>> X X
>>>>
>>>> On Wed, Nov 11, 2009 at 11:39 AM, Chris Dyer <[email protected]> wrote:
>>>>> Hi John-
>>>>> The first label is the orientation of the phrase pair with respect to
>>>>> its left context (on the source side), and the second is the
>>>>> orientation with respect to its right context.  That's why you have to
>>>>> have "swap other" or "other swap", since a phrase can only be inverted
>>>>> on one side.
>>>>> Hope this helps,
>>>>> Chris
>>>>>
>>>>> On Wed, Nov 11, 2009 at 2:34 PM, John DeNero <[email protected]> wrote:
>>>>>> Hi all,
>>>>>>
>>>>>> I'm trying to generate a replacement phrase extraction file to be used
>>>>>> in estimating a lexical reordering model.  I'm running
>>>>>> train-factored-phrase-model.perl with the "-reordering
>>>>>> msd-bidirectional-fe" flag, which generates an extract.o.gz file with
>>>>>> content like:
>>>>>>
>>>>>> reanudación ||| resumption ||| mono mono
>>>>>> reanudación del ||| resumption of the ||| mono mono
>>>>>> ...
>>>>>> este ||| this ||| swap other
>>>>>> ...
>>>>>>
>>>>>> I understand that the mono, swap, and other tags correspond to the
>>>>>> "(m) monotone order, (s) switch with previous phrase, or (d)
>>>>>> discontinuous" types described in the online Moses docs.  I don't
>>>>>> really understand what the two different tags correspond to, though.
>>>>>> What does the first entry vs. the second entry mean in each line?
>>>>>> Apologies if this is explained somewhere in the docs or mailing list
>>>>>> archives -- I didn't find it.
>>>>>>
>>>>>> Thanks,
>>>>>> John
>>>>>>
>>>>>> _______________________________________________
>>>>>> 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

Reply via email to