Difference between revisions of "Corpus Relation Extraction"
Anote2Wiki (talk | contribs) |
|||
| Line 1: | Line 1: | ||
[[Category:HOWTOs]] | [[Category:HOWTOs]] | ||
| − | + | To perform a '''Relation Extraction''' (RE) process based in Natutal Language Processing algorithms, you should right click a Corpus data-type object and select the option '''Corpus -> RE-> Relation Extraction'''. | |
| − | + | If the Corpus is not in the clipboard, you should begin by [[Load_Corpus|loading the Corpus to the Clipboard]]. | |
| − | |||
| − | |||
[[Image:Corpus_Process_RE.png|1500px|center]] | [[Image:Corpus_Process_RE.png|1500px|center]] | ||
| − | A new wizard | + | A new wizard is presented that allows to configure the RE process. |
| − | The first panel enables the '''selection''' of the '''processes''' that | + | The first panel enables the '''selection''' of the '''processes''' that contain the entities annotated, allowing to view some statistics and process properties. After selecting the process press '''Next''' to continue. |
[[Image:RE1.png|800px|center]] | [[Image:RE1.png|800px|center]] | ||
| − | Next | + | Next panel allows for '''POS-Tagger selection'''. Here, you select which POS-Tagger will be used, and some information about POS_Tagger properties will be present. After choosing the POS-Tagger press '''Next''' to continue. |
[[Image:RE2.png|800px|center]] | [[Image:RE2.png|800px|center]] | ||
| − | + | The following panel allows for '''Relation Extraction Model Selection'''. The user selects the most adequate model (the panel below shows the expected type of results). After selecting the best model press '''Next'''. | |
[[Image:RE3.png|800px|center]] | [[Image:RE3.png|800px|center]] | ||
| Line 25: | Line 23: | ||
[[Image:RE4.png|800px|center]] | [[Image:RE4.png|800px|center]] | ||
| − | + | The next panel allows choosing a '''Verb List'''. You can select a list of verbs (a Lexical Words object) are not co-notated as verbs in POS-Taggers to addition as Relation Clue. After the user must press '''Ok Button'''. | |
[[Image:RE5.png|800px|center]] | [[Image:RE5.png|800px|center]] | ||
Revision as of 14:28, 16 January 2013
To perform a Relation Extraction (RE) process based in Natutal Language Processing algorithms, you should right click a Corpus data-type object and select the option Corpus -> RE-> Relation Extraction.
If the Corpus is not in the clipboard, you should begin by loading the Corpus to the Clipboard.
A new wizard is presented that allows to configure the RE process. The first panel enables the selection of the processes that contain the entities annotated, allowing to view some statistics and process properties. After selecting the process press Next to continue.
Next panel allows for POS-Tagger selection. Here, you select which POS-Tagger will be used, and some information about POS_Tagger properties will be present. After choosing the POS-Tagger press Next to continue.
The following panel allows for Relation Extraction Model Selection. The user selects the most adequate model (the panel below shows the expected type of results). After selecting the best model press Next.
Proceeding, next panel is for choose Verb List Filter option. User can select a list of filter verbs (Lexical Words). This option, when selected, permits remove list of verbs from Relation Clues. For example, normally common English verbs like be, are not good indicators for Relations.
The next panel allows choosing a Verb List. You can select a list of verbs (a Lexical Words object) are not co-notated as verbs in POS-Taggers to addition as Relation Clue. After the user must press Ok Button.
RE operation will start and a small window will appear, indicating the execution of the operation. The REoperation will take a few minutes or hours, depending of corpus size.
When the process finishing, a new RE Process object will be added to the Corpus Process View.
