|
|
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]
| | <noinclude> |
| | This is the "AAType" template. |
| | It should be used with the form. |
| | </noinclude><includeonly> |
| | {{ #if: {{{Image|}}} | |
| | {{ #set:Image={{{Image|}}} }} |
| | [[File:{{{Image}}}|200px|thumb|left|{{PAGENAME}}]] |
| | | }} |
| | {{ #if: {{{Home page|}}} | |
| | <div class="tpldiv"><span class="tpllabel">Home page</span> |
| | <span class="tblvalue">[[Home page::{{{Home page|}}}]]</span> |
| | </div> |
| | | }} |
| | {{ #if: {{{Location|}}} | |
| | {{#arraymap:{{{Location}}}|,|x|[[Category:x]] |<nowiki> </nowiki>}} |
| | {{#arraymap:{{{Location}}}|,|x|[[Location::x]] |<nowiki> </nowiki>}} |
| | [[GPS Location::{{ #geocode:{{{Location}}}, Canada}}]] |
| | | }} |
| | {{ #if: {{{Arts|}}} | |
| | {{#arraymap:{{{Arts}}}|,|x|[[Category:x]] |<nowiki> </nowiki>}} |
| | <!-- {{#arraymap:{{{Arts}}}|,|x|[[Arts::x]] |<nowiki> </nowiki>}} --> |
| | | }} |
| | {{ #if: {{{Type|}}} | |
| | {{#arraymap:{{{Type}}}|,|x|[[Category:x]] |<nowiki> </nowiki>}} |
| | <!-- {{#arraymap:{{{Type}}}|,|x|[[Type::x]] |<nowiki> </nowiki>}} --> |
| | | }} |
| | {{ #if: {{{Aspects|}}} | |
| | {{#arraymap:{{{Aspects}}}|,|x|[[Category:x]] |<nowiki> </nowiki>}} |
| | <!-- {{#arraymap:{{{Aspects}}}|,|x|[[Aspects::x]] |<nowiki> </nowiki>}} --> |
| | | }} |
|
| |
|
| [[File:GATE_screenshot.png|900px|GATE developer screenshot]] | | {{ #ask: [[Category:Event]][[People::{{PAGENAME}}]] |
| | |?Start date |
| | |?End date |
| | |?Location |
| | |intro=<h2>Events with {{PAGENAME}}</h2> |
| | }} |
|
| |
|
| 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.
| | {{#forminput:form=Event|||button text=Add an event|query string=Event[People]={{PAGENAME}}&Event[Arts]={{{Arts}}}|}} |
|
| |
|
| = Using GATE developer = | | <br class="cleared" /> |
|
| |
|
| * GATE developer is used to process sets of Language Resources in Corpus using Processing Resources. They are typically saved to a serialized Datastore.
| | </includeonly> |
| * 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}
| |
| | |
| [[File:GATE-lucene-person-money.png]]
| |
| | |
| == 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, it needs usability testing, a lot of things are inobvious and too domain specific. It could really use some "sexying up," interaction could including a lot more useful and interesting looking displays. A web based version could have these features.
| |
| | |
| {{Blikied|Aug 30, 2010}}
| |
| | |
| [[Category:SemWeb]]
| |