330 likes | 512 Views
Pragmatic Interoperability. Guy Divita Qing Zeng- Trei tler Salt Lake City VA, University of Utah School of Medicine. Toy Story. We all agree one-off-solution is not good Many approaches to Interoperability. Internal Interoperabil ity. Framework Supporting Interoperability.
E N D
Pragmatic Interoperability Guy Divita Qing Zeng-Treitler Salt Lake City VA, University of Utah School of Medicine
Toy Story • We all agree one-off-solution is not good • Many approaches to Interoperability
Within System Issues Many Master Builders who do not share a plan! And plan changes…
Within System Issues Sometimes integration is more work than building from scrtach
Ontological Alignment
Feature Alignment Semantics
Feature Alignment Semantics (2)
Interoperability Efforts within v3NLP
Common Set of Labels • From survey of existing NLP systems • Common ontological referent points • Combines CDA, Penn Treebank labels • New labels where needed • Document structure (table, figure, snippet, slot value … • Rendered into • UIMA Type Descriptors • Protégée Ontology
Interoperability Efforts within v3NLP
Solution Some planning Simple protocol + Simple semantics Limit the number of moving parts
Pragmatic Interoperability Principles
NLP Ecosystem Elements • Programs, projects, ideas, utilities, services and shared resources • workflow aids, annotation editors, evaluation tools, lexicon generation aids, ontology development tools, dashboards • Repo’s, wiki’s, website(s) • Evolving standards, guidelines, best practices
NLP Ecosystem Elements (continued) • Big goals, grand challenges, many little dance steps • Engendering developer and user communities • Engendering collaborative environments • Governing body to influence direction • ……
… Toward a NLP Ecosystem Voogo cTAKES WEKA MetaMap Mallot RapTAT U Compare Sublanguage Model UIMA ARC Common Labels UIMA-GATE converter UFIT Dave EMMA Sophia
An Ecosystem that includes POS Tagger Corpus Annotation Analysis Text-To-Structured Data Annotation Tools Text Normalization (stemming) GATE Concordance Template Detection Negation Shallow NP Parser Relationship Identification UIMA Full Parser Temporal Relations Section Tokenizer Knowtator Text Simplification Document / Section / Sentence/ Phrase Information Retrieval indexes Local Terminology Development Tool NLP Standards Document Classifier Spelling Suggestion Concept: value Identification De-Identification Co-reference Resolution Term Identification Table Tokenization Word Sense Disambiguation Concept Identification Figure/Caption Identification Anaphora Resolution Semantic Classification Theme Detection Multi-Document Summarization – Novelty Detection Document Summarization