You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@joshua.apache.org by "Lewis John McGibbney (JIRA)" <ji...@apache.org> on 2016/04/05 07:31:25 UTC

[jira] [Updated] (JOSHUA-129) Constrained decoding heuristics aren't quite right

     [ https://issues.apache.org/jira/browse/JOSHUA-129?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Lewis John McGibbney updated JOSHUA-129:
----------------------------------------
    Fix Version/s: 6.1

> Constrained decoding heuristics aren't quite right
> --------------------------------------------------
>
>                 Key: JOSHUA-129
>                 URL: https://issues.apache.org/jira/browse/JOSHUA-129
>             Project: Joshua
>          Issue Type: Bug
>            Reporter: Matt Post
>             Fix For: 6.1
>
>
> To implement constrained decoding, we make sure that the LM state of each proposed node matches the input sentence. This is necessary but insufficient. See the test case in test/decoder/constrained, where some constrained sentences have multiple outputs not all equal to the constraints.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)