A Very Brief Overview of

1
A Very Brief Overview of Ontological
Semantics as Text Processing, Knowledge
Representation and Reasoning Substrate for the
Medical Mentor andfor Other Biomedical
Applications Sergei Nirenburg, Institute for
Language and Information Technologies University
of Maryland, Baltimore County
2
Ontological semantics is a computationally
tractable theory of meaning in natural language
as well as a suite (OntoSem) of implemented NLP
programs and a set of static knowledge resources
that support these programs. Ontological
semantics deals directly with extraction, represen
tation and manipulation of text meaning. Ontosem
text analyzers produce interpreted knowledge
ready to be used in reasoning-heavy applications
that include question answering, cross-document
and cross-lingual text summarization, question
answering, machine translation and others.
Support of intelligent human-computer
interaction in domain- and task-oriented
environments is squarelywithin the purview of
ontological semantics.
3
Ontological semantics concentrates on content of
representations and is adaptable to a number of
different representation formats. Ontological
semantics is both a producer and aconsumer of
knowledge deriving text meaning isitself a
knowledge-intensive task
4

• OntoSem
• is devoted to processing naturally occurring
  texts
• strives for high-quality results first
  followed by concern for broad coverage
• expects unexpected inputs
• seeks quality heuristics of any provenance
  (knowledge- based or probabilistic,
  cooccurrence-based)
• does not grant syntax a privileged position
  among the providers of heuristics for
  semantic processing
• does not make a strong distinction between
  semantics and pragmatics
• is applicable to any natural language

5
Ontological-semantic analyzers take natural
language texts as inputs and generate
machine- tractable text meaning representations
(TMRs) that form the basis of various reasoning
processes. Sample Input Sentence Iran, Iraq
and North Korea on Wednesday rejected an
accusation by President Bush that they are
developing weapons of mass destruction. The TMR
(presented graphically) for the above isas
follows
6
Output A Text Meaning Representation (TMR)
This presentation is simplified the system, in
fact, derives much more from text event
instances are shown in ellipses object
instances, in rectangles only caserole and set
membership relations are shown (as labels on
links) numerical constraints can be fuzzy, as
in the cardinality of SET-1226.
7
A pretty-printed fragment of the actual TMR
representation for sample input
8

• Ontological-semantic systems centrally rely on
  the following
• static knowledge resources
• a language-independent ontology that
  includes knowledge about types of
  entities in the world,
• e.g., ATHLETE, WELD or SPEED
• ontology-oriented lexicons (and onomasticons,
  or lexicons of proper names) for each
  natural language in the system and
• a fact repository containing instances of
  ontological concepts, e.g., Andre
  Agassi
• (ATHLETE-3176) or the Apollo 13 mission
  (SPACEFLIGHT-142)

9
A Sample Screen of the Ontology/Lexicon/Fact
Repository Browsing and Editing Environment
10
(No Transcript)
11
(No Transcript)
12
(diagnosis (diagnosis-n1 (cat n) (anno
(def "") (ex "The diagnosis (of cancer) (by
the specialist) was made quickly")
(comments "")) (syn-struc ((root var0)
(cat n) diagnosis (pp-adjunct
((root of) (root var1) (cat prep) (opt )
of (obj ((root var2) (cat n)))))
disease (pp-adjunct ((root by) (root
var3) (cat prep) (opt ) by (obj ((root
var4) (cat n))))))) someone
(sem-struc (DIAGNOSE
the ontological mapping (agent (value
var4)) the case roles (theme (value
var2))) (var1 (null-sem )) blocks
compositional analysis of preps (var3
(null-sem )))) )
13
(cancer (cancer-n1 (cat n) (anno (def "a
disease") (ex "") (comments "") )
(syn-struc ((n ((root var1) (cat n) (opt )))
animal part as modifier (root var0)
(cat n) cancer ))
(sem-struc (CANCER (location (value
var1) (sem animal-part))) ) )
14
(cancer-n2 (cat n) (anno (def "a sign of
the zodiac") (ex "") (comments "") )
(syn-struc ((root var0) (cat n) ))
(sem-struc (CANCER-ZODIAC) ) ) )
15

• Currently Available Static Knowledge Sources for
  English
• Ontology of about 6,500 concepts (about
  95,000 property-value pairs)
• English lexicon of about 40,000 entries
• Fact repository of about 20,000 facts (outside
  medical domain)
• English Onomasticon of about 350,000 entries
• Tokenization knowledge, morphological and
  syntactic grammars
• for a number of languages

16
The analyzers conceptual architecture
(in reality, not strictly pipelined)
TMR
SyntacticAnalyzer
SemanticAnalyzer
Preprocessor
Processing Modules
Grammar Ecology MorphologySyntax
Lexicon and Onomasticon
Ontology and Fact Repository
Static Knowledge Resources
17

• The basic (who did what to whom) semantic
  dependency is derived, in the general case, on
  the basis of
• lexical-semantic expectations (selectional
  restrictions) recorded in the ontology and the
  lexicon and
• syntactic dependency derived from the results of
  syntactic analysis.

18
The beginnings of system evaluation
Run I raw Run II preprocessor output
correct Run III preprocessor and syntactic
analysis output correct
19
In addition to the basic semantic dependency,
TMRs also include parameterized information
provided by the microtheoriesof aspect, modality
(including speaker attitudes), time, style and
others. Most of these microtheories have been
implemented. All would benefit from further
work. We are also actively looking
into possibilities of borrowing some
microtheories -- either in toto or partially.
20
(No Transcript)
21
In Phase I of the implementation of the Medical
Mentor, OntoSem will support a) system reasoning
b) evaluation of the work of the trainee c)
mentor intervention and d) training case study
preparation by using its ontology, fact
repository and GUI capabilities. A major
supporting knowledge source will be the
script, realized in the OntoSem ontology as the
content of the has-as-part property of complex
events (dynamic scripts) and objects (static
scripts). The typical, expected sequence of
operations by the trainee will be recorded in
workflow scripts.
22
Script diagnose top level
23
Script diagnose Track colon cancer
Complaint
Go see a doctor
Doctor performs test(s) to form hypothesis
Doctor asks questions
Above 50?
Y
Age?
Recent unintentional weight loss?
Yes?
Doctor forms hypothesis
Recent fatigue?
Contribute to possible colon cancer diagnosis
Working Hypothesis Colon cancer
Recent constipation?
Doctor chooses further tests
Test N
Recent change in bowel habits?
Y
Colonoscopy
Recent Stool color?
Test 2
Recent decrease in stool size?
Test confirms hypothesis?
History of ulcerative colitis?
24
(No Transcript)
25
Overall Architecture of a Generic Application of
Ontological Semantics
26
Knowledge acquisition for OntoSem is not an
overwhelming proposition. A combination of
expert acquisition and machine learning methods.
27
(No Transcript)
28
(No Transcript)
29
(No Transcript)
30
(No Transcript)
31
(No Transcript)
32
(No Transcript)
33
(No Transcript)
34
(No Transcript)
35
(No Transcript)
36
(No Transcript)