Question Answering Using Ontological Semantics 
Stephen BEALE, Benoit LAVOIE, Marjorie MCSHANE, Sergei NIRENBURG,Tanya KORELSKY 
 
Institute for Language and Information 
Technologies (ILIT-UMBC) 
1000 Hilltop Circle 
Baltimore, MD, USA 21250 
{sbeale,marge,sergei}@umbc.edu 
CoGenTex, Inc. 
840 Hanshaw Rd, Suite 1 
Ithaca, NY, USA, 14850 
{benoit,tanya}@cogentext.com 
 
Abstract 
This paper describes the initial results of an 
experiment in integrating knowledge-based 
text processing with real-world reasoning in a 
question answering system. Our MOQA 
“meaning-oriented question answering” 
system seeks answers to questions not in open 
text but rather in a structured fact repository 
whose elements are instances of ontological 
concepts extracted from the text meaning 
representations (TMRs) produced by the 
OntoSem text analyzer. The query 
interpretation and answer content formulation 
modules of MOQA use the same knowledge 
representation substrate and the same static 
knowledge resources as the ontological 
semantic (OntoSem) semantic text analyzer. 
The same analyzer is used for deriving the 
meaning of questions and of texts from which 
the fact repository content is extracted. 
Inference processes in question answering rely 
on ontological scripts (complex events) that 
also support reasoning for purely NLP-related 
purposes, such as ambiguity resolution in its 
many guises. 
1 The Task 
People would have no problem answering 
questions like Has Tony Hall met with Umid 
Medhat Mubarak? – provided they know who 
these two people are and have witnessed such a 
meeting or read about it. Even in the absence of 
overt evidence about such a meeting, people might 
conclude – based on additional knowledge they 
might have about the protagonists – that such a 
meeting could or might have taken place. Some 
current automatic question-answering (QA) 
systems might be able to answer such a question if 
they found a sentence like Tony Hall met with 
(saw, talked with) Umid Medhat Mubarak on July 
3, 2003 in Baghdad  in some text. But what if the 
text data was more typical, like, for instance, the 
following two excerpts: 
  
April 18, 2000  Associated Press. Representative 
Tony Hall, a Democrat from Ohio, arrived in 
Baghdad on a four-day visit to investigate the 
plight of Iraqi people under sanctions aimed at 
forcing the government of Iraq to give up its 
weapons of mass destruction… 
 
Umid Medhat Mubarak returned to Baghdad on 
April 17, 2000 after a visit to Jordan and plans to 
meet with a visiting US politician. 
 
To the best of our knowledge, no current system 
can input the above texts and return a reasoned 
response about the likelihood of a meeting between 
Tony Hall and Mubarak. But in a realistic 
environment there are even further complications. 
What if the first text was in English and the second 
in Arabic? Will the system be able to make even a 
tentative connection between Tony Hall (in the 
first text) and US politician (in the second)? What 
if the reference to US politician was omitted; i.e. if 
the second text contained only the information that 
Umid Medhat Mubarak was in Baghdad on April 
17, 2000? The system would have to infer the 
possibility of a meeting on the basis of knowledge 
about (at least) the social and professional 
background of the protagonists and the times 
involved. 
This paper describes a system that is able to 
make connections and inferences such as the 
above. Its most important properties are question 
answering against structured data stored in a fact 
repository (FR) and the fact that it uses the same 
processing machinery and knowledge resources a) 
to process texts for conversion into facts, b) to 
understand questions and c) to find answers to 
questions. We describe the underlying technology 
that supports such a capability, including the 
production of text meaning representations 
(TMRs), reference and date resolution, fact 
extraction and retrieval, and event scripts that 
allow us to infer (with some degree of probability) 
certain events or states not directly stated in any 
text. 
2 The Environment for QA 
Our question answering system consists of four 
main and one auxiliary processing modules (see 
Figure 1). The question analysis module takes as 
input the text of a user’s question and produces its 
text meaning representation (TMR, see below 
for an illustration) that contains representations of 
instances of ontological concepts to which the 
input refers plus speaker-attitude and 
communicative information. The TMR is input to 
the question interpretation module that interprets 
the question in terms of its type and transforms it 
into a formal query against the fact repository or 
the ontology (see below). (Note that the format of 
the database query is the same as that of the 
question TMR. In general, all internal 
representations of knowledge in our system, both 
elements of knowledge support and results of 
actual processing, are compatible with the content 
and format of the ontology and fact repository.)  
approach “doubles” as the basis for reasoning 
processes. T
content dete
the knowledge resources of the s
m
the TMR 
found,
auxiliary module for
knowledge, CSK
the background m
continuo
work reporte
involvem
CSK; we plan to stu
sy
When called by
m
generates 
answer the 
process in thi
question anal
is 
implementation simply returns fragments of facts 
(and fact reasoning chains) that answer the initial 
question. In the future, natural language generation 
will be employed to produce textual responses. 
In order to answer complex questions in context, 
a system must extract, manipulate and generate the 
meaning of natural language texts. Question 
answering against a structured knowledge base, 
especially when the latter contains interpretable 
knowledge elements (e.g., instances of events and 
objects defined in an ontology, not uninterpreted 
text strings), can attain better results than QA that 
works by manipulating templates filled with 
snippets of actual texts – at the least because of the 
added benefit of disambiguation and reference 
resolution. The prerequisite for such a system is 
the existence of a structured knowledge base used 
as a source of answers to questions. In a real 
application, the knowledge must be ample and 
dynamic, so that the knowledge resources must be 
constantly and promptly augmented. This is not 
practical if knowledge is acquired entirely by 
people. Automating structured knowledge 
acquisition from open text is, therefore, a 
necessary condition for the success of an advanced 
QA application. The CSK module of our system is 
Figure 1. The top-level architecture of the 
system. 
Thus, text meaning representation in our 
he query serves as input to answer 
rmination. This latter module uses 
ystem to infer the 
ost preferred answer, once again, formulated in 
metalanguage. If an answer cannot be 
 the system has the option to call the 
 creating structured 
. The CSK module works also in 
ode, using text sources to 
usly update the fact repository (in the 
d here there has been some human 
ent in the process of TMR production for 
dy the degradation of the 
stem when used in a fully automatic mode). 
 the answer content determination 
odule, the CSK module analyzes texts and 
entries in the fact repository that help to 
original question. The text analysis 
s module is the same as that used in 
ysis. The final module in the system 
answer formulation. The current 
a step toward this functionality, albeit not yet in a 
fully automatic way. At this point, we rely on 
TMRs that are obtained automatically but 
improved through human interaction (see 
Nirenburg et al. 2004 for details). Note that fully 
automatic methods for creating structured 
knowledge of a quality even remotely approaching 
that needed to support realistic QA do not at this 
point exist. Few of the numerous current and 
recent machine learning and statistical processing 
experiments in NLP deal with the analysis of 
meaning at all; and those that do address partial 
tasks (e.g., determining case role fillers in terms of 
undisambiguated text elements in Gildea and 
Jurafsky 2002) in a rather “knowledge-lean” 
manner. The results are very far away indeed from 
either good quality or good coverage, either in 
terms of phenomena and text. We believe that our 
approach, using as it does statistical as well as 
recorded-knowledge evidence for extracting, 
representing and manipulating meaning is the most 
practical and holds the most promise for the future. 
Indeed, it is not even as expensive as many people 
believe. 
3 The Knowledge Support Infrastructure 
The process of deriving TMRs from text is 
implemented in our Ontosem text analyzer. 
Semantic analysis in OntoSem is described in 
some detail in Nirenburg and Raskin 2004; 
Nirenburg et al., 2004; Beale et al. 1995, 1996, 
2003; Mahesh et al. 1997. Our description here 
will be necessarily brief.  Also note that the 
analysis process is described here as if it were a 
strict pipeline architecture; in reality, semantic 
analysis is used to inform and disambiguate 
syntactic analysis, for example, in cases of 
prepositional phrase attachment.  
Text analysis in OntoSem relies on the results of 
a battery of pre-semantic text processing modules. 
The preprocessor module deals with mark-up in 
the input text, finds boundaries of sentences and 
words, recognizes dates, numbers, named entities 
and acron
analy
generated the citation for
text, the s
entries in its l
lexicon of 
sa
ontological se
clause-level dependency
and assign gra
constituents (that is, est
objects, obliq
(m
the ontology 
carry
disam
dependencies in the text. The results a
in 
analy
m
attitudes and other knowledge elem
produced in OntoSem using a variety of 
“microtheories,” to produce extended TMRs. At 
both steps, the analyzer has to deal with ambiguity, 
incongruity between the input and the expectations 
recorded in the static knowledge sources (SKSs), 
unknown words, and non-literal language. In a 
recent evaluation, the basic analyzer was shown to 
carry out word sense disambiguation at over 90% 
and semantic dependency determination at 87% on 
the basis of correct syntactic analysis and on 
sentences of an average length of over 25 words 
with 1.33 unknown words on average per input 
sentence (see Nirenburg et al., 2004). While not yms and performs morphological 
sis. Once the morphological analyzer has 
ms for word forms in a 
ystem can activate the relevant lexical 
exicons, including the onomasticon (a 
proper names). Figure 2 presents a 
mple of preprocessor output.  
Figure 2: Sample preprocessor output 
Figure 3: Sample parser output, in graphical
The task of syntactic analysis (see Figure 3) in 
mantics is, essentially, to determine 
 structures for an input text 
mmatical categories to clause 
ablish subjects, direct 
ue objects and adjuncts). 
 
Semantic analysis proper uses the information 
utual constraints) in the active lexicon entries, 
and the results of earlier processing to 
 out, at the first step, word sense 
biguation and establish basic semantic 
re recorded 
basic TMRs (see below). At the next step, the 
zer determines the values of the various 
odalities, aspect, time, speech acts, speaker 
ents that are 
perfect, these results show promise as training data 
for machine learning work.  
The OntoSem ontology provides a 
metalanguage for describing the meaning of the 
lexical units in a language as well as for the 
specification of meaning encoded in TMRs. The 
ontology contains specifications of 
concepts corresponding to classes of 
things and events in the world. It is a 
collection of frames, or named sets of 
property-value pairs, organized into a 
hierarchy with multiple inheritance. The 
expressive power of the ontology and the TMR is 
enhanced by multivalued fillers for properties, 
implemented using the “facets” DEFAULT, SEM, 
VALUE, and RELAXABLE-TO, among others. At the 
time of this writing, the ontology contains about 
6,000 concepts (events, objects and properties), 
with, on average, 16 properties each. Temporally 
and causally related events are encoded as values 
of a complex event’s HAS-EVENT-AS-PART 
property. These are essentially scripts that provide 
information that is very useful in general reasoning 
as well as reasoning for NLP (e.g., Schank and 
Abelson 1977, Lin and Hovy 2000, Clark and 
Porter 2000). We use scripts in the answer content 
determination module of the question answering 
system. Figure 4 illustrates a rather simple script 
that supports reasoning for our example question 
answering session.  
     The OntoSem lexicon contains not only 
semantic information, it also supports 
morphological and syntactic analysis. 
Semantically, it specifies what concept, concepts, 
property or properties of concepts defined in the 
ontology must be instantiated in the TMR to 
account for the meaning of a given lexical unit of 
input. At the time of writing, the latest version of 
the English semantic lexicon includes over 12,000 
handcrafted entries. These entries cover some of 
the most complex lexical material in the language 
– “closed-class” grammatical lexemes such as 
conjunctions, prepositions, pronouns, auxiliary and 
modal verbs, etc. as well as about 3,000 of the 
For lack of space, we will not be able to discuss 
all the representational and descriptive devices 
used in the lexicon or the variety of ways in which 
semantic information in the lexicon and the 
ontology can interact. See Nirenburg and Raskin 
(2004, Chapters 7 and 8) for a discussion.  
MEET-WITH     
  (AGENT (VALUE $VAR1))     
  (THEME (VALUE $VAR2))     
  (LOCATION (VALUE $VAR3))     
  (TIME(VALUE $VAR4))     
 
 PRECONDITIONS     
  (AND         
  (LOCATION           
    (DOMAIN (VALUE $VAR1))           
    (RANGE (VALUE $VAR3))           
    (TIME (VALUE $VAR4)))        
  (LOCATION          
    (DOMAIN (VALUE $VAR2))         
    (RANGE (VALUE $VAR3))          
    (TIME (VALUE $VAR4))))     
 
 EFFECTS      
 (SPEECH-ACT        
   (AGENT (VALUE $VAR1))          
   (BENEFICIARY (VALUE $VAR2)))       
 (SPEECH-ACT        
   (AGENT (VALUE $VAR2))       
   (BENEFICIARY (VALUE $VAR1))) 
 
 
COME   
  (AGENT (VALUE $VAR1))   
  (DESTINATION (VALUE $VAR2))     
 
 EFFECTS     
 (LOCATION     
    (DOMAIN (VALUE $VAR1))      
   (RANGE (VALUE $VAR2))) 
 
 
LOCATION  
  (DOMAIN (VALUE $VAR1))  
  (RANGE (VALUE $VAR2))    
 
 EFFECT-OF     
 (COME       
   (AGENT (VALUE $VAR1))       
   (DESTINATION (VALUE $VAR2))) 
 
Figure 4: A sample script,  
presented in a simplified  
presentation format. 
The English onomasticon (lexicon of proper 
names) currently contains over 350,000 entries 
semantically linked to ontological concepts; it is 
increasing in size daily by means of semi-
automated knowledge-extraction methods. 
The TMR (automatically generated but shown 
here in a simplified presentation format) for a short 
sentence (He asked the UN to authorize the 
war) from a recently processed text about Colin 
Powell is presented below. The numbers associated 
with the ontological concepts indicate instances of 
those concepts: e.g., REQUEST-ACTION-69 means 
the 69
th
 time that the concept REQUEST-ACTION has 
been instantiated in the world model used for, and 
extended during, the processing of this text or 
corpus.  
 
REQUEST-ACTION-69  
    AGENT   HUMAN-72  
    THEME   ACCEPT-70  
    BENEFICIARY   ORGANIZATION-71  
    SOURCE-ROOT-WORD  ask  
    TIME     (< (FIND-ANCHOR-TIME))  
ACCEPT-70  
   THEME   WAR-73  
   THEME-OF   REQUEST-ACTION-69  
   SOURCE-ROOT-WORD   authorize 
ORGANIZATION-71  
   HAS-NAME   UNITED-NATIONS 
   BENEFICIARY-OF     REQUEST-ACTION-69  
   SOURCE-ROOT-WORD  UN 
HUMAN-72  
   HAS-NAME  COLIN-POWELL 
   AGENT-OF   REQUEST-ACTION-69  
   SOURCE-ROOT-WORD   he ; ref. resolution done 
WAR-73  
   THEME-OF     ACCEPT-70  
    SOURCE-ROOT-WORD  war  
most frequent main verbs. We illustrate the 
structure of the lexicon entry on the example of the 
first verbal sense of alert: 
 
alert-v1      
  cat    v   
  morph  regular  
   
  ex     "He alerted us to the danger" 
The above says that there is a REQUEST-ACTION 
event whose agent is HUMAN-72 (Colin Powell), 
whose beneficiary is ORGANIZATION-71 (United 
Nations) and whose THEME is an ACCEPT event. 
That ACCEPT event, in turn, has the THEME WAR-
73. Note that the concept ACCEPT is not the same 
as the English word accept: its human-oriented 
definition in the ontology as “To agree to carry out 
an action, fulfill a request, etc”, which fits well 
here.  
  syn-struc 
    subject   $var1          
 root    "alert" 
     indirectobject  $var2  
     pp   (opt +) 
    root  "to"  
  object $var3          
  sem-struc 
     WARN      
    agent   ^$var1   
      beneficiary  ^$var2 
      theme   ^$var3 
The Fact Repository contains a list of 
remembered instances of ontological concepts. For 
 
exa
concept 
for Lond
ontolo
repository
difference between an ontological concept and its 
instance is the nature of th
each. In the former, the fillers of properties ar
typicall
are a
unfilled when not known.
entry
4 
describe the
modules of Question Analy
Interpretation and Answer Content Det
Figure 5 shows a questio
exe
question in
and clicks on
analy
The TMR of the question, the result of the 
Question Analysis module, is displayed in the 
mple, whereas the ontology contains the 
CITY, the fact repository contains entries 
on, Paris and Rome; and whereas the 
gy contains the concept WAR, the fact 
 contains the entry WWII. The main 
e fillers of properties for 
e, 
y, overridable constraints; in the latter, they 
ctual values (when known), or they are left 
 A simple fact repository 
 is illustrated below: 
 
HUMAN-33599 
 NAME George W. Bush  
 ALIAS  
 George Bush,  
Figure 5: Querying about a known person.
  President Bush,  
 George W,  
 the president of the United States,  
 the US president 
 SOCIAL-ROLE  PRESIDENT 
 GENDER        male 
 NATIONALITY        NATION-213 ;(USA)  
 DATE-OF-BIRTH July 6, 1946 
 spouse  human-33966 ;Laura Bush 
The Question Answering Modules 
Referring back to Figure 1, we now will briefly 
 three central question answering 
sis, Question 
ermination.  
n answering session that 
mplifies these three stages. The user enters a 
 the “Natural Language Query” text box 
 the “Submit” button. The OntoSem 
zer is then invoked to analyze the question. 
Query Analysis Details box. Obviously, not many 
of the details can be seen in these figures, but in 
the interface, the user can scroll through the TMR 
output. We will, in fact, be integrating our existing 
TMR and Fact graphical browsers into this 
interface in the near future. The results of the next 
module, Question Interpretation, are then displayed 
in the Query Paraphrase box. From there, the fact 
repository is queried, an answer is returned 
(perhaps utilizing the inference techniques to be 
described), and the supporting fact (or fact 
reasoning chain) is displayed in the Answer Details 
box. Below we present three example sessions, the 
third of which will be the basis for the more 
detailed description of the three modules. 
For this discussion, we concentrate on the 
following three sentences that have been processed 
by the CSK module and the facts that were derived 
from them and stored in the fact repository (the 
facts are represented using instances of ontological 
concepts, of course): 
 
1. Tony Hall Met with Umid Medhat Mubarak. 
2. Tony Hall arrived in Baghdad (on Thursday). 
3. Ali Atwa was in Baghdad (on April 18 and 
later). 
 
In Figure 5, the question is “Who is Tony Hall?” 
In its current state, the system simply finds and 
responds with the stored fact about Tony Hall, 
which includes the information about his arrival 
(the COME-1003 event derived from sentence 2) 
and the MEET-WITH-1001 event (derived from 
sentence 1). Figure 6 shows the results of the 
query, “Did Tony Hall meet with Umid Medhat 
Mubarak?” A matching 
fact was found in the FR 
(derived from sentence 
1) and is displayed in the 
Answer Details. Figure 7 
presents a more complex 
case. The query is “Did 
Tony Hall meet with Ali 
Atwa?” The FR contains 
no fact that can directly 
answer this question. 
The system uses facts 
from sentences 2 and 3 
to return the possible 
inference MEET-WITH-
??? (the tentative nature 
of the inference is 
marked by the -??? 
appended as the instance 
number; and in the 
Figure 6: Querying about a known event. 
future, we will also generate a numerical value 
reflecting the confidence level of the inferences 
and sub-inferences). The supporting reasoning 
chain is also displayed. We will now use this 
example to discuss the three main question 
answering modules. 
The Question Analysis module takes the input 
text question and produces the TMR using the 
resources described in section 3 above. Figure 8 
illustrates the resulting TMR in a graphical 
browser. (One can inspect the content of the 
various concept instances – e.g., OBJECT-56 – by 
clicking on graphical objects representing them). 
The main thing to point out is that the TMR 
instantiates a MEET-WITH event which is the basis 
for querying the FR, itself comprised of facts 
represented by ontological concept instances. 
The Question Interpretation module then 
derives the canonical form of an 
input question TMR (determining 
question type and reformulating 
the content of an actual question 
in a standard format), and applies 
reference resolution. The answer 
displayed in Figure 7 involves 
reformulating the query Did $X 
meet with $Y? to Find meetings 
involving $X and $Y or more 
particularly, Find meetings where 
a person named $X is AGENT and 
a person named $Y is 
BENEFICIARY, and meetings 
where a person named $Y is 
AGENT and a person named $X is 
BENEFICIARY. Such a query can 
be specified as a standard DBMS 
query for the actual search. The knowledge that we 
are dealing with people and knowledge of their 
names is used to help resolve the references 
between the instances Tony Hall 
and Ali Atwa appearing in the 
query and the references to Tony 
Hall and Ali Atwa that may be 
stored in the fact repository. We 
will report on the actual methods 
of question interpretation and 
reference resolution we use 
separately.  
    The Answer Content 
Determination module is 
invoked next. The possible 
queries constructed in the 
previous module are processed. 
First, direct queries are attempted. 
If an answer is found, it is returned directly. In this 
example, no fact directly states that Tony Hall met 
Ali Atwa. Scripts are then activated which allow us 
to reason about the question. In the script of Figure 
4, the preconditions of a MEET-WITH event include 
both participants having to be in the same place at 
the same time. This will invoke a series of queries 
that will determine if Tony Hall and Ali Atwa were 
indeed in the same location at the same time. In 
general, if the preconditions of an event are 
satisfied, we infer that the event itself possibly 
took place. In this case, the fact that Ali Atwa was 
in Baghdad is present in the FR by virtue of 
sentence 3 above. Using this knowledge, the 
system seeks to prove that Tony Hall was also in 
Baghdad at the same time. Once again, there is no 
direct fact that states this. However, the facts about 
Tony Hall include information that he arrived in 
Baghdad at a certain time (at the present time, we 
do not attempt to match the times of the facts, 
although this will be a focus of our ongoing work). 
Figure 7: Querying about an unknown 
event. 
Matching times ofThis information is represented 
by the COME-1003 fact. We can look up COME in 
the script of Figure 4 and see that one effect of a 
COME event is that the agent’s location becomes 
the destination of the COME event. In general, we 
can use known facts to infer additional facts about 
their effects. In this case, we can infer that Tony 
Hall was, in fact, in Baghdad, which, in turn, 
allows us to make the top level inference that he 
might have met with Ali Atwa, who we previously 
determined was also in Baghdad. We are aware 
that the conjecture about the possible meeting 
should involve additional knowledge of the 
background and histories of the participants (e.g., 
if a cobbler and a head of state are in the same 
place at the  
potential meeting between 
on enhancin  
ontolo
reckoning.  
into m
There are 
including: 
•
•
•
environm
particular, the scripts that we are developing 
encode expectations and are 
direct the inference process – even we are fully 
aware of the abductive, defeasible nature of this 
knowledge.  
The inference steps described above were 
directed by the information in the MEET-WITH and 
COME scripts. Also, known facts about one of the 
participants, Tony Hall, were used to direct queries 
to support a possible inference. Obviously, much 
work remains to be done. We must populate a large 
fact repository that should include a large 
collection of facts about individuals as well as 
places, organizations and event instances. At this 
time, we are starting to use our TMR production 
environment for extracting facts. We hope to be 
able to report on the progress of this work at the 
workshop.  
5 Conclusion 
We have presented the first experiment with a 
knowledge-based QA system in which text 
processing is integrated with reasoning on the basis 
of shared knowledge and processing 
infrastructures. Indeed, the same processing and 
knowledge resources in the system carry out 
reasoning for the purposes of QA and reasoning 
that is necessary to create a high-quality 
unambiguous text meaning representation itself. 
While this is just a small experiment, we have 
specific and, we believe, realistic plans for scaling 
this system up – through automatic population of 
the fact repository, semi-automatic enlargement of 
the lexicons and the ontology and expansion of the 
inventory of scripts.  
Figure 8. Sample output viewed through the 
TMR browser 
We believe that integrating a comprehensive 
throughput system for an advanced application, 
even one in which some of the modules are still on 
a relatively small scale, is a very important kind of 
work in our field. It tackles real problems head on, 
 same time, that does not imply a
them). We are working 
g the knowledge (centered on the
gical MEET-WITH script) to improve such 
In a separate article in preparation, we will go 
uch more detail about the reasoning process. 
obviously many additional issues, 
 events. Our time resolution meaning 
procedures enable this; 
 Assigning probabilities to inferences. For 
example, if two people were in the same room, 
the possibility of their meeting is much higher 
than if they were in the same country; 
 Controlling the inference process. 
 
With regard to this last issue, the OntoSem 
ent provides a useful mechanism. In 
meant to constrain and 
without resorting to a rather defeatist – though 
quite common in today’s NLP – claim that certain 
goals are infeasible.  

References  
S. Beale, S. Nirenburg and K. Mahesh. 1995. 
Semantic analysis in the Mikrokosmos machine 
translation project. In Proceedings of the 2
nd
Symposium on Natural Language Processing, 
Kaset Sart University, Bangkok, Thailand.   
S. Beale, S. Nirenburg and K. Mahesh. 1996. 
Hunter-Gatherer: Three search techniques 
integrated for natural language semantics. In 
Proceedings of the 13th National Conference on 
Artificial Intelligence. Portland, OR.  
S. Beale, S. Nirenburg and M. McShane. 
2003. Just-in-time grammar. In Proceedings 
HLT-NAACL-2003, Edmonton, Canada. 
P. Clark and B. Porter. 2000. $RESTAURANT Re-
visited: A KM implementation of a compositional 
approach. Technical Report, AI Lab, University 
of Texas at Austin.  
D. Gildea and D. Jurafsky. 2002. Automatic 
labeling of semantic roles. Computational 
Linguistics 28(3). 245-288.  
C. Lin and E. H. Hovy. 2000. The automated 
acquisition of topic signatures for text 
summarization. In Proceedings of the COLING 
Workshop on Text Summarization. Strasbourg, 
France. 
K. Mahesh, S. Nirenburg and S. Beale. 1997. If 
you have it, flaunt it: Using full ontological 
knowledge for word sense disambiguation. In 
Proceedings of Theoretical and Methodological 
Issues in Machine Translation (TMI-97). Santa 
Fe, NM. 
S. Nirenburg and V. Raskin. 2004. Ontological 
Semantics.  MIT Press. 
S. Nirenburg, M. McShane and S. Beale.  2004.  
Evaluating the performance of OntoSem.  In 
Proceedings ACL Workshop on Text Meaning 
and Interpretation, Barcelona. 
R. Schank and R. Abelson. 1977. Scripts, plans, 
goals, and understanding. Hillsdale, NJ: 
Erlbaum. 
