the start and end points are still start and end. But the width no
longer means the number of words. I think Chris Dyer added the
floyd-walshall algorithm to find the shortest path between 2 points, but
that doesn't mean the number of words either.
The size of the phrase in the InputPath is the
Thanks, looks good. Does cur_hypo.GetCurrSourceWordsRange() still make
sense in the context of lattices?
On 30.06.2015 18:28, Hieu Hoang wrote:
> cur_hypo.GetTranslationOption().GetInputPath()
>
> i hope
>
> Hieu Hoang
> Researcher
> New York University, Abu Dhabi
> http://www.hoang.co.uk/hieu
>
cur_hypo.GetTranslationOption().GetInputPath()
i hope
Hieu Hoang
Researcher
New York University, Abu Dhabi
http://www.hoang.co.uk/hieu
On 30 June 2015 at 19:30, Marcin Junczys-Dowmunt wrote:
> Hi,
> is there a way to find the current source phrase (input path) for
> lattices in the following f
Hi,
is there a way to find the current source phrase (input path) for
lattices in the following feature function hook?
FFState* EvaluateWhenApplied(
const Hypothesis& cur_hypo,
const FFState* prev_state,
ScoreComponentCollection* accumulator)
Specifically I want to use the OSM with latt