[jira] [Resolved] (STANBOL-1123) Label Token matching should consider tokens that are marked as "consumed"

["Rupert Westenthaler (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/STANBOL-1123?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Rupert Westenthaler resolved STANBOL-1123.
------------------------------------------

    Resolution: Fixed

fixed with http://svn.apache.org/r1496359 (as part of STANBOL-1114)

> Label Token matching should consider tokens that are marked as "consumed"
> -------------------------------------------------------------------------
>
>                 Key: STANBOL-1123
>                 URL: https://issues.apache.org/jira/browse/STANBOL-1123
>             Project: Stanbol
>          Issue Type: Sub-task
>          Components: Enhancement Engines
>            Reporter: Rupert Westenthaler
>            Assignee: Rupert Westenthaler
>
> Tokens marked as "consumed" should be considered while matching Labels of Entities with the processed Text.
> Marking Tokens as "consumed" aims to reduce the number or required vocabulary lookups. However considering those while matching does not hurt performance while it dose increase the quality of the linking process.
> Allowing so will bring improvements especially for very long noun phrases, where an initial query (typically by using the first to nouns) might not suggest the best matching Entity. Person mentions like "{role} {given} {given} {family}" are typical examples for such cases.



--
This message was sent by Atlassian JIRA
(v6.1#6144)