Semantic Annotation for Semantic Indexing

1
Semantic Annotation for Semantic Indexing

• Paul Buitelaar, Martin Volk
• MuchMore
• DFKI Language Technology
• Saarbrücken, Germany
• Eurospider Information Technology AG
• Zürich, Switzerland

2
Overview
MuchMore Objectives

• Linguistic/Semantic Annotation
• General Architecture
• Annotation Format
• Demo

• Semantic Indexing
• Indexing
• Results

3
MuchMore Objectives
Evaluation Systematic Comparison of
Cross-Lingual Information Retrieval (CLIR)
Methods on a Realistic Scenario in the Medical
Domain ? Establishing a Baseline with
Corpus-Based Methods ? Comparison with
Concept-Based Methods

• Concept-Based CLIR
• Effective Use of Medical and General Semantic
  Resources with
• Term and Relation Tagging
• Term Extraction and Classification
• Sense Disambiguation

4
Linguistic/Semantic Annotation
Lexicons
PoS, Morph, Chunks
Corpus or Document Collection
Term Tagging
EWN
Sense Disambiguation
UMLS
Relation Tagging
Annotated Corpus / Document Collection in XML (MM
Format)
Semantic Indexing (CL)IR
Knowledge Markup Semantic Web
Ontology Development Term Classification Relation
Discovery
...
5
Annotation Format (DTD)
id

code

from

pref

umlstrms

umlsterm

to

tui

cui

msh

code

id

xrceterms

xrceterm

from

pref

to

tui

cui

msh


id

term1
semrels

semrel

term2
type
document

sentence

ewnterms

ewnterm

sense

offset
id

gramrels

gramrel

type

id

from

chunks

chunk

to

type

text

token

id

pos

lemma

6
Demo