Proceedings of the
Second Workshop on
Text Meaning and Interpretation
Held in cooperation with ACL-2004
25–26 July 2004
Barcelona, Spain
Copyright cAD2004 The Association for Computational Linguistics
Order copies of this and other ACL proceedings from:
Association for Computational Linguistics (ACL)
73 Landmark Center
East Stroudsburg, PA 18301
USA
Tel: +1-570-476-8006
Fax: +1-570-476-0860
acl@aclweb.org
Second Workshop on Text Meaning and Interpretation 25–26 July 2004
Preface
This 1
1
2
-day workshop will continue the success of the 2003 Workshop on Text Meaning, which was held
at the Human Language Technology Conference of the North American Chapter of the Association for
Computational Linguistics in Edmonton. It aims to:
AF re-establish the research community of knowledge-based interpretation of text meaning;
AF explicate the implicit treatments of meaning in current knowledge-lean approaches and how they and
knowledge-rich methods can work together; and
AF emphasize the construction of systems that extract, represent, manipulate, and interpret the meaning
of text (rather than theoretical and formal methods in semantics).
Most, if not all, high-end NLP applications—such as machine translation, question answering and text
summarization—stand to benefit from being able to use text meaning in their processing. But the bulk of
work in the field in recent years has not pertained to treatment of meaning. The main reason given is the
complexity of the task of comprehensive meaning analysis and interpretation.
Computational linguistics has always been interested in meaning, of course. The tradition of formal
semantics, logics, and common-sense reasoning system has been continuously maintained for many years.
But also, much work has been devoted to building practical, increasingly broad-coverage meaning-oriented
analysis and synthesis systems. Lexical semantics has made significant progress in theories, description,
and processing. Formal aspects of ontology work have also been studied. The Semantic Web has further
popularized the need for automatic extraction, representation, and manipulation of text meaning: for the
Semantic Web to really succeed, capability of automatically marking text for content is essential, and this
cannot be attained reliably using only knowledge-lean, semantics-poor methods.
While there has recently been a flurry of specialized meetings devoted to formal semantics, lexical
semantics, semantic web, formal ontology and others, the number of meetings devoted to knowledge-based
text meaning processing—content rather than formalism—has been much smaller. The first Workshop on
Text Meaning began to remedy this, and ten papers were presented on implemented systems and on related
topics.
1
The call for papers of the present workshop suggested, without limitation, the following topics to poten-
tial contributors to the workshop:
AF Implemented systems that extract, represent, or manipulate text meaning.
AF Broad-coverage semantic analysis and interpretation.
AF Knowledge-based text synthesis.
AF The nature of text meaning required for various practical broad-coverage applications.
AF Manual annotation of text meaning, including interlingual annotations.
AF Pragmatics and discourse issues as parts of meaning extraction and manipulation.
AF Ontologies supporting automatic processing of text meaning.
AF Semantic lexicons.
AF Microtheories to support text meaning extraction and manipulation: aspect, modality, reference, etc.
AF Text meaning representations in semantic analysis.
1
The proceedings of this workshop are available at http://acl.ldc.upenn.edu/W/W03/#W03-0900.
AF Reasoning to support semantic analysis and synthesis.
AF Multilingual aspects of meaning representation and manipulation.
AF Integrating semantic analysis and non-semantic language processing.
AF Semantic analysis and synthesis systems based on knowledge-lean stochastic corpus-oriented meth-
ods.
The call for papers encouraged discussion of theoretical issues that are relevant to computational applica-
tions, including descriptions of processors and static knowledge resources. It specifically preferred discus-
sions of content and meaning over discussions of formalisms for encoding meaning, and discussions of
decision heuristics in processing over discussions of generic processing architectures and theorem-proving
mechanisms.
Twenty-seven papers were submitted to the workshop, of which fifteen were selected for presentation
and are included in these proceedings. In addition, two panel sessions were organized—see descriptions
below in this volume.
Sergei Nirenburg and Graeme Hirst
July 2004
iv
Organizers
GRAEME HIRST, Department of Computer Science, University of Toronto. gh@cs.toronto.edu
SERGEI NIRENBURG, Department of Computer Science and Electrical Engineering, University of Mary-
land, Baltimore County. sergei@umbc.edu
Program Committee
JAN ALEXANDERSSON, Deutsche Forschungszentrum f¨ur K¨unstliche Intelligenz, Saarbr¨ucken
COLLIN BAKER, International Computer Science Institute, Berkeley
PETER CLARK,Boeing
DICK CROUCH, Palo Alto Research Center
RICHARD KITTREDGE, University of Montreal
PAUL KINGSBURY,Penn
TANYA KORELSKY, CoGenTex, Inc.
CLAUDIA LEACOCK, Educational Testing Service
DAN MOLDOVAN, University of Texas at Dallas
ANTONIO MORENO ORTIZ, University of M´alaga
MARTHA PALMER, University of Pennsylvania
GERALD PENN, University of Toronto
VICTOR RASKIN, Purdue University
ELLEN RILOFF, University of Utah
GRAEME RITCHIE, University of Edinburgh
MANFRED STEDE, University of Potsdam
KARIN VERSPOOR, Los Alamos National Labs
YORICK WILKS, University of Sheffield
v
Table of Contents
Interpretation in a cognitive architecture
HaroldParedes-Frigolett.........................................................................1
Solving logic puzzles: From robust processing to precise semantics
Iddo Lev, Bill MacCartney, Christopher Manning and Roger Levy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
Constructing text sense representations
Ronald Winnem¨oller...........................................................................17
OntoSem and SIMPLE: Two multi-lingual world views
MarjorieMcShane,MargalitZabludowski,SergeiNirenburgandStephenBeale......................25
Evaluating the performance of the OntoSem semantic analyzer
SergeiNirenburg,StephenBealeandMarjorieMcShane...........................................33
Question answering using ontological semantics
Stephen Beale, Benoit Lavoie, Marjorie McShane, Sergei Nirenburg and Tanya Korelsky. . . . . . . . . . . . . .41
Making sense of Japanese relative clause constructions
TimothyBaldwin..............................................................................49
Carsim: A system to visualize written road accident reports as animated 3D scenes
Richard Johansson, David Williams, Anders Berglund and Pierre Nugues . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57
Inducing a semantic frame lexicon from WordNet data
Rebecca Green and Bonnie Dorr . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .65
Paraphrastic grammars
Claire Gardent, Marilisa Amoia and Evelyne Jacquey . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 73
Lexical-semantic interpretation of language input in mathematical dialogs
Magdalena Wolska, Ivana Kruijff-Korbayov´a and Helmut Horacek . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81
Underspecification of ‘meaning’: The case of Russian imperfective aspect
Barbara Sonnenhauser . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 89
Text Understanding with GETARUNS for Q/A and Summarization
Rodolfo Delmonte . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 97
Semantic forensics: An application of ontological semantics to information assurance
VictorRaskin,ChristianF.HempelmannandKatrinaE.Triezenberg...............................105
Interpreting communicative goals in constrained domains using generation and interactive negotiation
Aur´elianMax................................................................................113
ix
Technical Program Schedule
Sunday, 25 July 2004
08:30–08:40 Welcome
08:40–09:10 Interpretation in a cognitive architecture
Harold Paredes-Frigolett
09:10–09:40 Solving logic puzzles: From robust processing to precise semantics
Iddo Lev, Bill MacCartney, Christopher Manning and Roger Levy
09:40–10:00 Constructing text sense representations
Ronald Winnem¨oller
10:00–10:30 Break
10:30–12:00 Panel: Toward a theory of semantic annotation
David Farwell and Eduard Hovy (conveners)
12:00–13:30 Lunch
13:30–14:00 OntoSem and SIMPLE: Two multi-lingual world views
Marjorie McShane, Margalit Zabludowski, Sergei Nirenburg and Stephen Beale
14:00–14:30 Evaluating the performance of the OntoSem semantic analyzer
Sergei Nirenburg, Stephen Beale and Marjorie McShane
14:30–15:00 Question answering using ontological semantics
Stephen Beale, Benoit Lavoie, Marjorie McShane, Sergei Nirenburg and Tanya Korelsky
15:00–15:30 Break
15:30–15:50 Making sense of Japanese relative clause constructions
Timothy Baldwin
15:50–16:10 Carsim: A system to visualize written road accident reports as animated 3D scenes
Richard Johansson, David Williams, Anders Berglund and Pierre Nugues
16:10–17:40 Panel: Can we move from sentence meaning to text meaning?
Sergei Nirenburg (convener)
Monday, 26 July 2004
08:30–09:00 Inducing a semantic frame lexicon from WordNet data
Rebecca Green and Bonnie Dorr
09:00–09:30 Paraphrastic grammars
Claire Gardent, Marilisa Amoia and Evelyne Jacquey
09:30–10:00 Lexical-semantic interpretation of language input in mathematical dialogs
Magdalena Wolska, Ivana Kruijff-Korbayov´a and Helmut Horacek
vii
10:00–10:30 Break
10:30–11:00 Underspecification of ‘meaning’: The case of Russian imperfective aspect
Barbara Sonnenhauser
11:00–11:20 Text Understanding with GETARUNS for Q/A and Summarization
Rodolfo Delmonte
11:20–11:40 Semantic forensics: An application of ontological semantics to information assurance
Victor Raskin, Christian F. Hempelmann and Katrina E. Triezenberg
11:40–12:00 Interpreting communicative goals in constrained domains using generation
and interactive negotiation
Aur´elian Max
viii
ix
Workshop Panels
Toward a Theory of Semantic Annotation
Conveners:  David Farwell, New Mexico State University and Universidad Politecnica de
Catalunya, and Eduard Hovy, Information Sciences Institute, University of Southern Cali-
fornia
Panelists:  Manfred Pinkal, Universität des Saarlandes, and Martha Palmer, University of
Pennsylvania
Given the increasing number of annotated corpora being created, it is opportune to consider
what one needs to do to ensure that the annotation effort succeeds. What, indeed, is “success”
for an annotation effort?  What desiderata should annotation efforts conform to in order to
maximize chances of success?  When compromises on the desiderata are required for practi-
cal reasons, which desiderata are first to go?  What is the resulting impact on the effort?
We propose the following desiderata:
• perform annotations that are useful for a wide number of tasks (possibly ones not even
foreseen today);
• focus on annotations not easily done automatically without having the corpus available as
training data;
• only annotate when high inter-annotator agreement is possible;
• focus on annotation that is fast and cheap (relatively), that doesn’t require lots of annota-
tor training, and that doesn’t require years to carry out;
• ensure that the annotations are theoretically well-founded and acceptable to a large num-
ber of people in various projects;
• build on previous efforts, and use automated tools to speed up annotation if possible;
• pay particular attention to annotation interface design, since this can significantly impact
performance.
In order to meet these desiderata, many annotation efforts have made decisions that may
be seen as compromises.  For example, by using the Penn Treebank texts, one can count on a
commonly-understood parse tree syntax.  However, the Treebank is not a balanced corpus,
and hence may negatively influence the results annotations that reflect phenomena not present
in that corpus.
On the panel, members of three semantic annotation projects will describe their work and
provide insights as to where they had to make compromises in the light of the desiderata and
why they did so:
• SALSA (Manfred Pinkal)
• PropBank (Martha Palmer)
• IL-Annotation (David Farwell and Eduard Hovy)
Can we move from sentence meaning to text meaning?
Convener:  Sergei Nirenburg, University of Maryland, Baltimore County
Panelists:  TBA
Text meaning as a whole has not yet attracted widespread attention.  Recent studies usually
concentrate on text-meaning components — propositional meaning within a single sentence
or even clause, relations among clauses, or co-reference issues.  Earlier “holistic” work on
x
text-level “grammars” or plot units did not reach the stage where the main ideas were ripe for
judgments of explanatory power or utility.  One can indeed view text meaning as a combina-
tion of the meaning of its clauses plus causal, temporal, rhetorical, and other relevant relations
among the clause meanings, plus speaker attitudes expressed in the input text.  At this level, a
central issue is cross-fertilization of heuristic material — how one can use findings in one
component of the overall text meaning as heuristics for establishing elements of another com-
ponent?  For example, the propositional meaning of a clause can contribute to establishing a
coreferential relation between the meaning of a noun phrase within it and a noun phrase in
another clause.
Extracting and manipulating the meaning of an entire text holds the promise of improving
the quality of results in information extraction, automatic population of knowledge bases, text
summarization, modeling question answering and other intelligent agent systems that com-
municate with people, and other applications.  The needs of specific applications effectively
define the scope and depth of text meaning in specific projects.  The spectrum of choices here
is very broad — from approximating text meaning through textual collocation (the “knowl-
edge-lean” end of the spectrum) to including in text meaning the results of reasoning — for
example, judgments about speaker goals and beliefs (the “knowledge-rich” end). The choice
is made by balancing two conflicting desiderata — real utility and feasibility.  In this discus-
sion, we will analyze the available choices and assess the practicality and the promise of inte-
grating work on different components of text meaning.
Author Index
Amoia, Marilisa. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .73
Baldwin,Timothy...................................................................................49
Beale,Stephen...............................................................................25,33,41
Berglund, Anders . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57
Delmonte, Rodolfo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 97
Dorr, Bonnie . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65
Farwell,David......................................................................................ix
Gardent,Claire.....................................................................................73
Green, Rebecca . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65
Hempelmann,ChristianF. ..........................................................................105
Horacek, Helmut . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81
Hovy,Eduard.......................................................................................ix
Jacquey,Evelyne....................................................................................73
Johansson,Richard..................................................................................57
Korelsky,Tanya.....................................................................................41
Kruijff-Korbayov´a,Ivana............................................................................81
Lavoie,Benoit......................................................................................41
Lev,Iddo............................................................................................9
Levy,Roger.........................................................................................9
MacCartney, Bill . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
Manning, Christopher . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
Max, Aur´elian.....................................................................................113
McShane,Marjorie...........................................................................25,33,41
Nirenburg,Sergei..........................................................................ix,25,33,41
Nugues, Pierre . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57
Paredes-Frigolett,Harold.............................................................................1
Raskin,Victor.....................................................................................105
Sonnenhauser, Barbara . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 89
Triezenberg,KatrinaE. ............................................................................105
Williams, David. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .57
Winnem¨oller,Ronald ...............................................................................17
Wolska,Magdalena.................................................................................81
Zabludowski,Margalit...............................................................................25
121
