|
|
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]
| | /* CSS placed here will be applied to all skins */ |
| | /* @import "/css/basic.css"; */ |
| | @import "/css/galleriffic-3.css"; |
|
| |
|
| [[File:GATE_screenshot.png|900px|GATE developer screenshot]]
| | .tpllabel { |
| | float: left; |
| | width: 15%; |
| | } |
|
| |
|
| 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.
| | .tplvalue { |
| | float: right; |
| | width: 83%; |
| | } |
|
| |
|
| = 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.
| | h1.firstHeading { |
| * ANNIE, VG (verb group) processors.
| | display: none; |
| * 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 =
| | .cleared { |
| | clear: both; |
| | } |
|
| |
|
| * IR - retrieve docs
| | td.month_name { |
| * IE - retreive structured data
| | font-size: large; |
| | } |
|
| |
|
| * Knowledge Engineering - rule based
| | #p-logo a { background: url(/images/smacw3.png) 35% 50% no-repeat !important; } |
| * Learning Systems - statistical
| |
|
| |
|
| Old Bailey IE project - old english (Online)
| | .noticebox { |
| | -moz-border-radius: 1em; |
| | -webkit-border-radius: 1em; |
| | background: #eee; |
| | padding: 5px; |
| | } |
|
| |
|
| * POS - assigned in Token (noun, verb, etc)
| | .hidden { |
| | | display: none; |
| * 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]]
| |