fixing the beam it might be possible. Looking @ the code, it may be
happening already.
HypothesisStackNormal::PruneToSize()
However, another source of problem is the order in which hypotheses are
expanded. For the cube pruning algorithm, this in score order. For the
normal algorithm, it's any order, which in practice is influenced by LM
state. The order probably also slightly affect the resulting hypothesis set.
As Christian says, he attempted to solve this but hit issues. We've
thought about it but it just seems to be fitting square pegs into round
holes. Since it has negligible affect on BLEU, we gave up.
suppose it's good to talk about it and bear it in mind @ some point
On 25/03/2011 13:18, "Венцислав Жечев (Ventsislav Zhechev)" wrote:
> Here is what I think about this whole issue.
>
> Wouldn’t it be much more beneficial to the whole community to fix the basic
> beam search issue in Moses that seems to be the root of the problem, rather
> than write papers investigating it? As far as I understand, the issue most
> likely arises from the fact that the beam width limit might cut off some
> hypotheses from a group with equal probability, while leaving some for
> further processing. The fix would include checking the beam border and
> including all hypotheses with the least permissible probability, regardless
> of the actual beam width. This might require some redesign of the data
> structures that hold the hypotheses (I’m writing this without actually
> inspecting the source code), but this cannot be an untenable task. Let’s say
> this takes 8–16 man-hours to code and another 8–16 to test. Any volunteers in
> academia?
>
>
> Cheers,
>
> Ventzi
>
> –––––––
> Dr. Ventsislav Zhechev
> Computational Linguist
>
> CMS& Language Technologies
> Localisation Services
> Autodesk Development Sàrl
> Neuchâtel, Switzerland
>
> http://VentsislavZhechev.eu
> tel: +41 32 723 9122
> fax: +41 32 723 9399
>
>
> _______________________________________________
> 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
