GATE track 1 session: Difference between revisions

From zooid Wiki
Jump to navigation Jump to search
Line 1: Line 1:
A full week of learning [http://en.wikipedia.org/wiki/General_Architecture_for_Text_Engineering GATE] text mining/information extraction language processing and talks. [http://gate.ac.uk/wiki/TrainingCourseAug2010/ Session wiki]
{{Wiki_List |
wiki_name  =                CookBookWiki                                            |
wiki_logo =                  [[Image:NoLogo.png]]                                  |
wiki_URL =                  http://www.cookbookwiki.com/Main_Page                                                            |
wiki_recentchanges =        http://www.cookbookwiki.com/Special:Recentchanges                                                |
wiki_status =              Vibrant                    |
wiki_lastreviewed  =        16-Jan-06                  |
wiki_language =            English                    |
wiki_editmode =            OpenEdit            |
wiki_engine =              MediaWiki                  |
wiki_maintopic =            Food
}}
==Description==
A cooking wiki with over 20,000 recipies and cooking related articles


[[File:GATE_screenshot.png|900px|GATE developer screenshot]]
Our mission is to document every culinary tradition of the world. Every culture that has existed has a rich tradition of preparing and using food. Until now, that has only been captured in fragments, spread over thousands of books. These books go out of print and are lost to the majority of mankind. We want to bring all of these tradition together and preserve them for future generations.


GATE is written in Java and very Java centric. This makes it portable, fast, and heavyweight. A programming library is available.  It's 14 years old and has many users and contributors.
Read our {{tag|Mission Statement}}(http://www.cookbookwiki.com/Cookbookwiki:About) Check out the wiki's:
 
{{tag|Development Road Map}}
= Using GATE developer =
 
* GATE developer is used to process sets of Language Resources in Corpus using Processing Resources. They are typically saved to a serialized Datastore.
* ANNIE, VG (verb group) processors.
* Preserve formatting embeds tags in HTML or XML.
** Different strengths using GATE's graph (node/offset) based XML vs. preserved formatting (original xml/html)
 
= Information Extraction =
 
* IR - retrieve docs
* IE - retreive structured data
 
* Knowledge Engineering - rule based
* Learning Systems - statistical
 
Old Bailey IE project  - old english (Online)
 
* POS - assigned in Token (noun, verb, etc)
 
* Gazateer - gotcha, have to set initialization parameter listsURL before it's
loaded. Must also "save and reinitialize."
* Gazeteer creates Lookups, then transducer creaties named entities
* Then orthomatcher (spelling features in common) coreference associates those
 
* Annotation Key sets and annotation comparing
** Need setToKeep key in Document Reset for any pre annotated texts
 
== Evaluation / Metrics ==
 
* Evaluation metric - mathematically against human annotated
* Scoring - performance measures for annotation types
 
* Result types - Correct, missing, spurious, partially correct (overlapped)
 
* Tools > Annotations Diff - comparing human vs machine annotation
 
* Corpus > Corpus quality assurance - compare by type
* (B has to be the generated set)
 
* Annotation set transfer (in tools) - transfer between docs in pipeline
** useful for eg HTML that has boilerplate
 
= Other notes =
 
== Lucene data store ==
 
* Use <null> for default set
* Go to Datastore for queries
** eg {Person}({Token})+{Money}
* Useful for debugging JAPE and results
 
[[File:GATE-lucene-person-money.png|800px]]
 
== To investigate ==
 
* markupAware for HTML/XML (keeps tags in editor)
* AnnotationStack
* Advanced Options
 
= JAPE =
 
* Rules based on tokens and lookups
 
== To review, gotchas ==
 
* Rule types : first takes only first match, excludes compound
** a? b for "a b" will match "a b"
* multiplexor tranducers
* multi-constraint statements
* macros
* To reuse created annotations has to be a separate rule
 
= To follow up =
 
* WebSphinx crawler CREOLE plugin
 
= Conclusions =
 
While it can do a lot out of the box and benefits from development time and breadth of connectivity, to be useful to more than patient specialists, it needs usability testing. A lot of things are inobvious and too domain specific that with a bit of work could be more broadly useful. Interaction could include a lot more immediate, useful and interesting looking displays. A web based version could have these features. However the team seems somewhat ambivalent about development. :)
 
{{Blikied|Aug 30, 2010}}
 
[[Category:SemWeb]]

Revision as of 15:58, 3 September 2010

Template:Wiki List

Description

A cooking wiki with over 20,000 recipies and cooking related articles

Our mission is to document every culinary tradition of the world. Every culture that has existed has a rich tradition of preparing and using food. Until now, that has only been captured in fragments, spread over thousands of books. These books go out of print and are lost to the majority of mankind. We want to bring all of these tradition together and preserve them for future generations.

Read our Template:Tag(http://www.cookbookwiki.com/Cookbookwiki:About) Check out the wiki's: Template:Tag