. . . . q

Proceedings of the Ninth-International Workshop on

Natural Language Generation

Niagara-on-the-Lake, Ontario, Canada 5-7 August 1998

Sponsored by the Association for Computational Linguistics

!

! !

J .

Welcome

The study of automated Natural Language Generation has had a long and varied history. Usually overshadowed by larger efforts in parsing, semantic analysis, grammar development, lexical studies, and lately statistical processing, progress is slower in NLG than in some other areas of Computational Linguistics. And though the importance of the topic has always been recognized, the difficulty of the topic has usually not been appreciated by most people not directly involved with generation. Undeservedly, generation is often seen as somewhat easier than parsing and semantic analysis, simply because it is easier to build a low-quality realizer than a low-quality parser or analyzer. But when the stages of text planning and sentence planning are factored in, and the problem of expressive variation is faced, the true complexity of generation becomes apparent. That's when one sees the need for much deeper theories of discourse, lexis, and pragmatics than are currently available!

NLG has been fortunate, though, in having a dedicated and loyal core set of practitioners. Their ongoing concern is reflected in the active workshop series. About a decade after some of the first papers on sentence generation appeared, the first NLG Workshop was held. Soon, the international workshops became a regular biennial series, alternating between North America and Europe. From the rather modest beginning as a small workshop in Germany in 1983, the INLG workshop has become a sought-after event, regularly attended by around 60 researchers: Stettenfels, Germany (1983); Stanford University, California (1984); Nijmegen, The Netherlands (1986); Santa Catalina Island, California (1988);~ Dawson,

• Pennsylvania (1990); Trento, Italy (1992), Kennebunkport, Maine (1994); Herstmonceaux, England (1996); Niagara-on-the-Lake, Canada (1998). • In addition, the European workshops, held in the intervening years since 1987, have also become an ongoing series.

We are in the fortunate position today of being able to wonder whether we should change the workshops into conferences. This year, an unprecedentedly large number of papers was st/bmitted. Registration soon reached capacity• O f near 100. The traditional number of around 60 attendees seems to be a thing• of the past. New projects, on all aspects of NLG, seem to be thriving.

There are also encouraging signs of awareness of the need to fund NLG research, and of its practical utility in commercial systems. The European Union, some European countries, some larger Japanes e software companies, and the Canadian Goyernment have shown continued willingness to fund NLG. Even the decade-long absence of funding from the larger US funding agencies may perhaps soon come to an end.

Many thanks are due to the following sponsors: • the University of Waterioo's Institute for Computer Research (ICR), for funding, administrative supplie s,

and the services of Jean Webster; • • the AmericanAssociation for Artificial Intelligence (AAAI), for funding to support student attendance; • the University of Waterl0o's Academic Development Fund, for funding of administrative costs.

I would like to thank the program committee and the local arrangements committee, listed at left, for their• very hard work in making this workshop so Successful. Special thanks to Chrysanne DiMarco and Graeme Hirst, who continued the tradition of holding the workshop in very pleasant surroundings.

With all this positive news, welcome to the i998 international natural language generation workshop!

Eduard Hovy, Program Chair Information Sciences Institute Marina del Rey, CA June, 1998

111

Table of Contents

• P a p e r s

Natural L a n g u a g e Genera t ion Journeys tO Interact ive 3D Wor lds . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 James C. Lester, William H. Bares, Charles B. Callaway, Stuart G. Towns (North Carolina State University, Raleigh, USA)

C o m m u n i c a t i v e goa l -d r iven N L generat ion and data-dr iven graphics generat ion: A n archi tectural synthesis fo r mul t imed ia page generat ion . . . . . . . . . . . 8

John Bateman, Thomas Kamps, Ji~rg Kleinz, Klaus Reichenberger (University of Stirling, Scotland/Darmstadt University, Germany)

A pr incip led representat ion o f at tr ibutive descript ions for generat ing integrated text and in format ion graphics presentat ions . . . . . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~. . . . . . . . . . . . . . . . . . . . . . . . . . . ~... 18

. : :i Nancy •Green, Giuseppe Carenini, Johanna Moore • (University Of Pittsburgh~ USA) An archi tecture for opportunis t ic text generat ion . . . : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i . . . , . . . . . . . . . . . . . . . 28 . . . . Chris Mellish, Mick O'Donnell, .Ion Oberlander, Alistair Knott

(University of Edinburgh, Scotland) Cont ro l l ed real izat ion o f complex objects by revers ing the Output o f a parser . . . . . . . : . . . . . . . . . . . . . . . . . . 38

David McDonald (Gensym Corp, Boston MA, USA)

De-cons t ra in ing text genera t ion . . . . . . . . . . . . . . . . . . . . . . . , . . . . . . . . . . . . . . . : . . . . . . . . . . . . . . . . . . . . ~... 48 • i Stephen Beale, Sergei Nirenburg, Evelyne Viegas, Leo Wanner

( CRL; New Mexico State University, USA) A u t o m a t i c genera t ion o f subway directions: Sal ience gradat ion as a factor for determining .

m e s s a g e and f o r m . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58

Lidia Fraczak, Guy Lapalme, Michael Zock (LIMSI-CNRS, Orsay, France/University of Montreal, Canada)

In t roduc ing m a x i m a l var ia t ion in text planning for small domains . . . . . . . . . . . . . . . . . . . ; . . . . . . . 68 Erwin Marsi

• (University Of Nijmegen, The Netherlands) A new approach to exper t system explanat ions 78

• Regina Barzilay, Daryl McCullough, Owen Rambow, Jonathan DeChristofaro . . . . Tanya Korelsky, Benoit Lavoie ( CoGenTex lnc.; Ithaca~Columbia University, New York~University of Delaware, USA)

M a c r 0 P l a n n i n g w i t h a cogni t ive archi tecture for the adapt ive explanat ion o f proofs 88 Armin Fiedler (University of the Saarland, Saarbriicken, Germany)

Expe r imen t s us ing stochast ic search for text planning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 98 Chris Mellish, Alistair Knott, Jon Oberlander, Mick O'Donnell (University of Edinburgh, Scotland)

A b d u c t i v e reasoning for syntactic real izat ion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .... . . . . . . . . . . . 108

• RalfKlabunde, Martin Jansche (University of Heidelberg, German),/Ohio state University, Columbus, USA)

Genera t ing warn ing instructions by planning acc idents and injuries . . . . . .... . . . . . . . . . . . . . . . . . . . . . 118 Daniel Ansari, Graeme Hirst (University of Toronto, Canada)

Discourse marker cho ice in sentence planning . . . . . . . . . . . . . . 128

Brigitte Grote, Manfred Stede (University of Magdeburg, Germany / TU Berlin, Germany)

i v

I

I [I I I ,I i l

I I tl II i.! !1 !1 I !

• i l

I

li

Clause aggregat ion using linguistics knowledge . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~ 138 James Shaw (Columbia University, New York, USA)

A u e n t i o n during a rgument generat ion and presentation 148 lngrid Zukerman, Richard McConachy, Kevin Korb . . . . (Monash University, Melbourne, Australia)

Planning dia logue contributions with new information . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . , . . . . . . . . . . . . . . 158 Kristiina Jokinen, Hideki Tanaka, Akio Yokoo (ATR Research Laboratories, Kyoto, Japan)

Genera t ion o f noun compounds in Hebrew: Can syntactic knowledge be fully encapsulated? 168 Yael Dahan Netzer, Michael Elhadad (Ben Gurion University, Israel)

Textual economy through close coupl ing o f syntax and semantics . . . . . . . . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . 178 Matthew Stone, Bonnie Webber (University of Pennsylvania, Philadelphia, USA)

A language- independent system for generat ing feature structures f rom in te r i inguarepresen ta t ions , 188 Murat Temizsoy, llyas Cicekli (Bilkent University, Ankara, Turkey)

Toward mult i l ingual protocol generat ion for spontaneous speech dialogues . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 198 Jan Alexandersson, Peter Poller (DFKI, Saarbriicken, Germany)

Ful ly lexical ized head-driven syntactic generat ion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 208

Tilman Becker (DFKI, Saarbriicken, Germany)

Approaches to surface realization with H P S G . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 218 Graham Wilcock (University of Manchester, England)

The Mul tex generator and its environment : Applicat ion and deve lopment . . . . . . . . . . . . . . . . . . . . . . . . . . . . 228 Christian Matthiessen, Licheng Zeng, Marilyn Cross, Ichiro Kobayashi, Kazuhiro Teruya, Canzhong Wu (Macquarie University, Sydney, Australia)

A f lexible shal low approach to text generat ion 238 Stephan Busemann, Helmut Horacek (DFKI, Saarbriicken, Germany)

The practical value of n-grams in generat ion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 248

• Irene Langkilde, Kevin Knight (USC/ISI, Marina del Rey, USA)

Generat ion as a solution to its own problem . . . . . . . . . . . . . . . . . . . . . . . . . . ~ . . . . . . . . . . . . : . . . . . . . . . . ~ . . . . . . . r ...... 256

Donia Scott, Richard Power, Roger Evans (ITRI, Brighton, England)

E X E M P L A R S : A practical, extensible f ramework for dynamic text generat ion . 266 Michael White and Ted CaMwell (CoGenTex Inc., Ithaca NY, USA)

System demonstration descriptions

Amal ia : N L G with abstract machine .... . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Evgeniy Gabrilovich, Nissim Francez, Shuly Wintner (Technion, Haifa, Israel / University of Tiibingen, Germany)

Circsum-Tutor! Content planning in a tutoring system . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Reva Freedman, Stefan Brandle, Michael Glass, Jung Hee Kim, Yujian Zho u, Martha Evens (University of Pittsburgh / Illinois Institute of Technology, USA )

276

280

V

. - • . •

F L A U B E R T : U s e r - f r i e n d l y m u l t i l i n g u a l N L G . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

Frdddric Meunier, Laurence Danlos (TALANA UFR Linguistique, Paris, France)

G B G e n : L a r g e - s c a l e d o m a i n - i n d e p e n d e n t G B s y n t a x ....

Thierry Etchegoyhen, Thomas Wehrle ~" " ............. ~" ~ ........ :'" ............. ~ ........ (LATL and FPSE, University of Geneva, Switzerland)

G o a l G e t t e r : G e n e r a t i o n o f s p o k e n s o c c e r r e p o r t s . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ; . . . .

Mari#t Theune, Esther Klabbers (IPO, Eindhoven University of Technology, The Netherlands)

M L W F A : M u l t i l i n g u a l w e a t h e r f o r e c a s t i n g s y s t e m . . . . . . . . . . . . . . . : . . . . . . . . . . . . , . . .

Tianfang Yao, Dongmo Zhang, Qian Wang (Shanghai Jiao Tong University, Shanghai, China)

M u l t i M e t e o : I n t e r a c t i v e g e n e r a t i o n o f w e a t h e r r e p o r t s , . . . . . . . . . . . . . : . . . . . . . . . . . . . ~ . . . . . . . r . . . . . . . . . .

• Josd Coch (ERLI, Charenton-le-Pont, France)

R O M V O X : T e x t - t o - s p e e c h s y n t h e s i s o f R o m a n i a n . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

Attila Ferencz, Teodora Ratiu, Maria Ferencz, Tiinde-Csiila Kovacs, Istvdn Nagy, Diana Zaiu (Technical University/Software ITC, Cluj-Napoca, Romania)

WYSIWYM: Knowledge editing with NL feedback . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i . . . . . . . . . . . . . . . . . . . . . . . .

Richard Power, Donia Scott. (ITRL University of Brighton, England) i

284

288

292

296

300

304

308

. • . .

vi

I I I

I il

I !1 i

I i

i

L

! I

i L _ .

I

Tuesday, August 4

18:00 Reception 19:30 Dinner

Workshop Program

Wednesday, August 5

Session 1: Planning and Generation with Multiple Media 8:30 Opening 8:45 Invited talk: Natural Language Generation J0umeys to Interactive D Worlds

James C. Lester, William H. Bares, Charles B. Callaway, Stuart G. Towns 9:30 Communicative Goal-Driven NL Generation and Data-Driven Graphics Generation:

An Architectural Synthesis for Multimedia Page Generation John Bateman, Thomas Kamps, Jtrg Kleinz, Klaus Reichenberger

10:00 A Principled Representation of Attributive Descriptions for Generating Integrated Text and

10:30

Information Graphics Presentations Nancy Green, Giuseppe Carenini, Johanna Moore

Break

Session 2: Architectural Questions 11:00 An Architecture for Opportunistic Text Generation

Chris Mellish, Mick O'Donnell, Jon Oberlander, Alistair Knott 11:30 Controlled Realizatio n of Complex Objects by Reversing the Output of a Parser

David McDonaM 12:00 De-Constraining Text•Generation

Stephen Beale, Sergei Nirenburg, Evelyne Viegas, Leo Wanner

12:30 Lunch

Session 3: Joint Planning of Content and Formulation • 14:00 Automatic Generation of Subway Directions; Salience Gradation as a Factor for Determining

Message and Form Lidia Fraczak, Guy Lapalme, Michael Zock

14:30 Introducing Maximal Variation in Text Planning for Small Domains Erwin Marsi '

14:45 A New Approach to Expert System Explanations Regina Barzilay, Owen Rainbow, Daryl McCullough

15:00 Macroplanning with a cognitive Architecture for the Adaptive Explanation of Proofs Armin Fiedler

15:15 Discussion

15:30 Break

Outing 16:00 22:30

Scenic tour to Niagara Falls and dinner Return to hotel

vii

Thursday, August 6

Session 4: Sentence Planning 1: Inference and Content 9:00 Experiments Using Stochastic Search for Text Planning

Chris Mellish, Alistair Knott, Jon Oberlander, Mick O'Donnell 9:30 Abductive Reasoning for Syntactic Realization

Ralf Klabunde, Martin Jansche 10:00 Generating Warning Instructions by Planning Accidents and Injuries

Daniel Ansari, Graeme Hirst

10:30 Break

Session 5: Sentence Planning 2: Subtnsks 11:00 Discourse Marker Choice in Sentence Planning

Brigitte Grote, Manfred Stede • 11:30 ~ Clause Aggregation using Linguistics Knowledge

James Shaw 1 i:45 Attention during Argument Generation 'and Presentation

lngrid Zukerman, Richard McConachy, Kevin Korb 12:00 Planning Dialogue Contributions with New Information

Kristiina Jokinen, Hideki Tanaka, Akio Yokoo " 12:15 Discussion

12:30. Lunch

. : ::. " Session 6: • !4:00

14i30

14:45

15:00

.15:15

.15:30

Relationships between Semantics, Syntax, Lexis, and Morphology Generation of Noun Compounds in Hebrew: Can Syntactic Knowledge be Fully Encapsulated? Yael Dahan Netzer, Michael. Elhadad Textual EconOmy through Close Coupling of Syntax and Semantics Matthew Stone, Bonnie Webber

- A Language-IndePendent System for Generating Feature Structures From Interlingua Representations Murat Temizsoy, llyas Cicekli Toward Multilingual Protocol Generation for Spontaneous Speech Dialogues Jan Alexandersson, Peter Poller. DiscussiQn . • • .

Break

System demonstrations (2 sessions,-in parallel) 16:00 FLAUBERT

User-friendly multilingual NLG Frdddric Meunier, LaurenceDanlos

16:20 GoalGetter Generation of spoken soccer reports Mari~t Theune, Esther Klabbers

16:00

16:20

ROMVOX Text-to-speech synthesis Of Romanian Attila Ferencz, Teodora Ratiu, Maria Ferencz, Tiinde-Csilla Kovdcs, lstvdn Nagy, Diana Zaiu

MultiMeteo Interactive weather reportgeneration - Jos~ Coch

t 6:40 GBGen Large-scale domain-indep. GB syntax Thiert T Etchegoyhen, Thomas Wehrle i

16:40

viii

MLWFA " Multilingual weather forecasts Tianfang Yao, Dongmo Zhang, Qian Wang

I I I i I i i

l i i

!1 I

i I !

17:00

17:20

Amalia NI_,G with Abstract Machine for Typed Feature Structures Evgeniy Gabrilovich, Nissim Francez, Shuly Wintner

WYSIWYM Knowledge editing with NL feedback Richard Powe r, Donia Scott

• 18:00 Dinner

17:00 Circsnm-Tutor Content planning in a tutoring system Reva Freedman, Stefan Brandle, Michael Glass, Jung Hee Kim, Yufian Zhou, Martha Evens

Friday, August 7

Session 7: Realization: Deep and Shallow Grammars 9:00 Fully Lexicalized Head-Driven Syntactic Generation

9:15

9:30

9:45

10:00

10:15

Tilman Becker Approaches to Surface Realization with HPSG Graham Wilcock The Multex •Generator and its Environment: Application and Development Christian Matthiessen, Licheng Zeng, Marilyn Cross, Ichiro Kobayashi, Kazuhiro Teruya,

" Canzhong Wu A Flexible Shallow Approach tO Tex t Generation Stephan Busemann and Helmut Horacek The Practical Value of N-Grams in Generation Irene Langkilde, Kevin Knight Discussion

10:30 Break

Session 8: Constructing the Input i1:00 Generation as a Solution to its Own Problem

Donia Scott, Richard Power, Roger Evans EXEMPLARS: A Practical, Extensible Framework for Dynamic Text Generation Michael White, Ted Caldwell ~ - Discussion

11:15

11:30

Panel •11:45

12i3o

Reference Architectures for Language Generators . Eduard Hovy. (moderator), Stephan Busemann, Robert Dale, Chris Mellish, Donia Scott

Lunch

I . . . . ix

Author List

J a n A l e x a n d e r s s o n . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 198 T o w a r d M u l t i l i n g u a l P r o t o c o l G e n e r a t i o n f o r S p o n t a n e o u s S p e e c h D i a l o g u e s

D a n i e l A n s a r i . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 118 G e n e r a t i n g W a r n i n g I n s t r u c t i o n s b y P l a n n i n g A c c i d e n t s a n d I n j u r i e s

W i l l i a m H. B a r e s . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . : . . . . . . . . . . . . . . . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2

N a t u r a l L a n g u a g e G e n e r a t i o n J o u r n e y s to I n t e r a c t i v e 3 D W o r l d s

R e g i n a B a r z i l a y . . . . . . . . , . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . : . . . . . . . . . . . 7 8

A N e w A p p r o a c h to E x p e r t S y s t e m E x p l a n a t i o n s

J o h n B a t e m a n . . . . : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

• C o m m u n i c a t i v e G o a l - D r i v e n N L G e n e r a t i o n a n d D a t a - D r i v e n G r a p h i c s G e n e r a t i o n :

A n A r c h i t e c t u r a l S y n t h e s i s f o r M u l t i m e d i a P a g e G e n e r a t i o n

i S t e p h e n B e a l e . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 D e - C o n s t r a i n i n g T e x t G e n e r a t i o n

T i l m a n B e c k e r . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~.. 2 0 8

F u l l y L e x i c a l i z e d H e a d - D r i v e n S y n t a c t i c G e n e r a t i o n

S t e f a n B r a n d l e . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . : : . . . . . . . . : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 8 0

C i r c s u m - T u t o r : C o n t e n t P l a n n i n g in a T u t o r i n g S y s t e m (system demo) S t e p h a n B u s e m a n n . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 3 8

A F l e x i b l e S h a l l o w A p p r o a c h to T e x t G e n e r a t i o n

T e d C a l d w e l l . . . . . . . . . . . . . . . ~ . . . . ~ . . : . . . . . . . L . . . : . . . . . . . .~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . : . . . : . . . . 2 6 6

E X E M P L A R S - A P r a c t i c a l , E x t e n s i b l e F r a m e w o r k fo r D y n a m i c T e x t G e n e r a t i o n •

C h a r l e s B . C a l l a w a y . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . : . . . . . . . : 2

N a t u r a l L a n g u a g e G e n e r a t i o n J o u r n e y s to I n t e r a c t i v e 3 D W o r l d s

G i u s e p p e C a r e n i n i . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~ . . . . . : . . . . . . . . . . . . . . . . . . . 18

A P r i n c i p l e d R e p r e s e n t a t i o n o f A t t r i b u t i v e D e s c r i p t i o n s fo r G e n e r a t i n g I n t e g r a t e d T e x t a n d

I n f o r m a t i o n G r a p h i c s P r e s e n t a t i o n s

I l y a s C i c e k l i . . . . . . : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ..~ . . . 1 8 8

A L a n g u a g e - I n d e p e n d e n t S y s t e m fo r G e n e r a t i n g F e a t u r e S t r u c t u r e s f r o m I n t e r l i n g u a

R e p r e s e n t a t i o n s

J o s 6 C o c h . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 0 0

M u l t i M e t e o : I n t e r a c t i v e w e a t h e r r e p o r t g e n e r a t i o n (system demo) M a r i l y n C r o s s . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 2 8

T h e M u l t e x G e n e r a t o r a n d i ts E n v i r o n m e n t : A p p l i c a t i o n a n d D e v e l o p m e n t

Y a e l D a h a n N e t z e r . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 168

• G e n e r a t i o n o f N o u n C o m p o u n d s in H e b r e w : C a n S y n t a c t i c K n o w l e d g e be F u l l y E n c a p s u l a t e d ?

L a u r e n c e D a n l o s . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~ . . . . . , . . . . . . . , . . . . . . . 2 8 4

F L A U B E R T : U s e r - f r i e n d l y m u l t i l i n g u a l NLG(system demo) • J o n a t h a n D e C h r i s t o f a r o . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i . . . . . . . . . 7 8

A N e w A p p r o a c h to E x p e r t S y s t e m E x p l a n a t i o n s

M i c h a e l E l h a d a d . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 168 G e n e r a t i o n o f N o u n C o m p o u n d s in H e b r e w : C a n S y n t a c t i c K n o w l e d g e b e F u l l y E n c a p s u l a t e d ?

T h i e r r y E t c h e g o y h e n . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 8 8

G B G e n : L a r g e - s c a l e d o m a i n - i n d e p e n d e n t G B s y n t a x (system demo) R o g e r E v a n s . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . : . . . . . . . . . . . . . . . . 2 5 6

G e n e r a t i o n as a S o l u t i o n to i t s O w n P r o b l e m

M a r t h a E v e n s . . . . . . . . . . . . . . . . . . . . . . i. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i . . . . . . . . . . ; . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 8 0

C i r c s u m - T u t o r : C o n t e n t P l a n n i n g in a T u t o r i n g S y s t e m (system demo) A t t i l a F e r e n c z . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~. . . . . . . . . . . . . . . 3 0 4

R O M V O X : T e x t - t o - s p e e c h s y n t h e s i s o f R o m a n i a n (system demo) M a r i a F e r e n c z . . . . . . . . . . " . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .~ 3 0 4

R O M V O X ' . T e x t - t o - s p e e c h s y n t h e s i s o f R 0 m a n i a n (system demo)

!

i! I ! ! !! I !

i! F!

j! ,!

¸.ill

!

! ! ! !

! ! l i I ! !

I I

Amain Fiedler . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 88 Macrop lann ing with a Cogn i t ive Archi tecture for the Adapt ive Explanat ion o f Proofs

L id ia Fraczak . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 8 Automat ic Genera t ion o f Subway Directions: Sa l ience Gradat ion as a Factor for Determining

Message and Form Niss im Francez . . . . . . . . . . . . . . . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 276

Amalia : N L G with Abstract Machine(system demo) R e v a F reedman . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 280

C i rc sum-Tu to r : Content Planning in a Tutor ing Sys tem (system demo) E v g e n i y Gabr i lov ich . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 276

Amal ia : N L G with Abstract Machine(system demo) Michae l Glass . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 280

Circsum-Tutor : Content Planning in a Tutor ing System (system demo) N a n c y Green . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

A Principled Representat ion o f At t r ibut ive Descript ions for Generat ing Integrated Tex t and Informat ion Graphics Presentat ions

Brigi t te Grote . . . . . . . . . . . . . . . . . . . . . . . ; . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . r ' - - " . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128 • Discourse Marker Choice in Sentence Planning

G r a e m e Hirst . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 118 Genera t ing Warning Instructions by Planning Accidents and Injuries

• He lmut Horacek . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 238

A Flexib le Shal low Approach to Tex t Generat ion Mart in Jansche . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 108

Abduc t ive Reason ing for Syntact ic Real iza t ion Krist i ina Jokinen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 158

Planning Dia logue Contributions with New Informat ion Thomas Kamps . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

C o m m u n i c a t i v e Goa l -Dr iven N L Generat ion and Data-Driven Graphics Generat ion: An Architectural Synthesis for Mul t imedi a Page Generat ion

Jung Hee Kim . . . . ; . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 280

Circsum-Tutor : Content Planning in a Tutor ing System (system demo) Esther Klabbers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 292

GoalGet ter : Generat ion o f spoken soccer reports (system demo) R a l f Klabunde . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 108

Abduc t ive Reason ing for Syntact ic Real izat ion J r r g Kleinz . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

C o m m u n i c a t i v e Goa l .Dr iven N L Generat ion and Data-Driven Graphics Generat ion: • An Architectural Synthesis for Mul t imedia P a g e Generat ion

Kevin Knight . . . . . . . . . . . . . . . ~. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 248

The Practical Value of N-grams in Generat ion Alistair Knott . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 98

Exper iments Using Stochastic Search for Tex t Planning 28 o , . . . . . . ° o o o ° ° . o o . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ° . . . . . . . . . . . . . . . . . . . . . ~ . . . . . . . . . . . . . ° ° ° o ° ° .

An Archi tec ture for Opportunist ic Text Genera t ion Ichiro Kobayashi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 228

The Mul tex Generator and its Environment : Appl icat ion and Deve lopmen t Kev in Korb . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 148

Attent ion during Argument Generat ion and Presentat ion Tanya Kore lsky . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78

A N e w Approach to Exper t Sys tem Explanat ions T0nde-Csi l la Kov~cs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 304

R O M V O X : Text- to-speech synthesis of Roman ian (system demo) Irene Langki lde . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . :. . . . . . . . . . . . . . . . 248

The Practical Value of N-grams in Generat ion

xi

Guy Lapa lme . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58

Au toma t i c Genera t ion o f Subway Direct ions: Sa l ience Gradat ion as a Fac tor for De te rmin ing M e s s a g e and F o r m

Beno i t Lavo ie . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78

A N e w A p p r o a c h to Exper t Sys t em Explana t ions

J ames C. Les ter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2

Natural Language Genera t ion Journeys to Interact ive 3D Wor lds

E r w i n M a r s i . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68

In t roduc ing M a x i m a l Var ia t ion in Tex t P lann ing for Smal l Domains

Chr i s t i an Mat th ie s sen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 228

The M u l t e x Genera to r and its Env i ronment : Appl ica t ion and D e v e l o p m e n t

R ichard M c C o n a c h y ..: . . . . . . . . . . . . . . i . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 148

At t en t ion dur ing A r g u m e n t Genera t ion and Presen ta t ion

D a r y l M c C u l l o u g h . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78

A N e w A p p r o a c h to Exper t S y s t e m Explana t ions

Dav id M c D o n a l d . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38

Cont ro l l ed Real iza t ion o f C o m p l e x Objec ts by Reve r s ing the Output o f a Parser

Chr i s M e l l i sh . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . , 9 8

E x p e r i m e n t s U s i n g Stochast ic Search for Text P lann ing

" . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . " . . . . . . . . . . . . . . . . " . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 8

A n Arch i tec tu re for Oppor tunis t ic Tex t Genera t ion

Fr6d6ric M e u n i e r . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 284

F L A U B E R T : User - f r i end ly mult i l ingual N L G (system demo) Johanna M o o r e . . . . . . . . . . . . . . . . . . . . . . . . . . . :~. . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .~. . 18

A Pr inc ip led Represen ta t ion o f At t r ibut ive Descr ip t ions for Genera t ing Integrated Text and

In fo rma t ion Graph ics Presenta t ions

Istv~in N a g y 304

R O M V O X : Tex t - to - speech synthes is o f Ro man i an (system demo) Sergei Ni renburg i . . . . . . . . . . . . . . . . . . ; . , . i . . . . . . . . . . . . . " . i . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .. . . . . . . . . . . . . . . . . . 48

De-Cons t r a in ing Tex t Genera t ion

Jon Obe r l ande r . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~. . . . . . . . . . . . . . . . . . . . . . . . : . . . . . . . . . . ~..: . . . . 98

E x p e r i m e n t s U s i n g Stochas t ic Search for Tex t P l a n n i n g . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . , . . . . 28

A n Arch i tec tu re fo r Oppor tunis t ic Text Genera t ion

M i c k O ' D o n n e l l . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 98

E x p e r i m e n t s U s i n g Stochast ic Search for Text P lann ing . . . . . . . . . . . : . . . . . . . : . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28

An Arch i tec tu re for Oppor tunis t ic Tex t Genera t ion

P e t e r Po l l e r . . : . . . . i . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 198

T o w a r d Mult i l ingual Protocol Genera t ion for Spon taneous Speech Dia logues

R ichard P o w e r . . . . . . . . . . . . . . . . . . . . . . . . . . . . .. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 5 6

Gene ra t ion as a Solut ion to its O w n P ro b l em , . . . . . . . . . . . . . . . . . . . . . : . . . . . . . . ~ . , . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 308

W Y S 1 W Y M : K n o w l e d g e edi t ing wi th N L feedback (system demo) O w e n R a i n b o w . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78

A N e w A p p r o a c h to E x p e r t S y s t e m Explana t ions • T e o d o r a Ratiu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . L . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 304

R O M V O X : Tex t - t o , speech synthes is Of R o m a n i a n (system demo) Klaus R e i c h e n b e r g e r . . . . . . . . i.. • . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

C o m m u n i c a t i v e Goa l -Dr iven N L Genera t ion and Data -Dr iven Graphics Generat ion:

A n Archi tec tura l Synthes is for Mul t imed ia Page Genera t ion

D o n i a Sco t t . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 256

Gene ra t ion as a Solut ion t o its O w n P r o b l e m • " • 308

W Y S I W Y M : K n o w l e d g e edi t ing with N L feedback (system demo)

xii

! ! ! ! !

! I

i

!! !

!

II

James Shaw " 138 Clause Aggregation using Linguistics Knowledge

Manfred Stede 128 Discourse Marker Choice in Sentence Planning

Matthew Stone . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . , . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 178 Textual Economy through Close Coupling of Syntax and Semantics

Hideki Tanaka . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . , . . . 158 Planning Dialogue Contributions with New Information

Murat Temizsoy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i 88 A Language-Independent System for Generating Feature Structures from Interlingua

Representations Kazuhiro Teruya . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ; . . . . . . . . . . . . . . . . . . . . 228

The Multex Generator and its Environment: Application and Development Mari& Theune . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 292

GoalGetter: Generation of spoken soccer reports (system demo) Stuart G. Towns . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2

Natural Language Generation Journeys to Interactive 3D Worlds Evelyne Viegas . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48

De-Constraining Text Generation Qian Wang 296

MLWFA: Multilingual Weather Forecasting System (system demo) Leo Wanner . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48

De-Constraining Text Generation Bonnie Webber . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 178

Textual Economy through Close Coupling of Syntax and Semantics Thomas Wehrle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 288

GBGen: Large-scale domain-independent GB syntax (system demo) Michael White . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 266

EXEMPLARS: A Practical, Extensible Framework for Dynamic Text Generation G r a h a m Wilcock . . . . . . . . . . . ,. 218

Approaches to Surface Realization with I-IPSG Shuly Winmer 276

Amalia: NLG with Abstract Machine(system demo) Canzhong Wu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 228

The Multex Generator and its Environment: Application and Development Tianfang Yao . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ; . . . . . . . . . . . . . . . . . . 296

MLWFA: Multilingual Weather Forecasting System (system demo) Akio Yokoo . 158

Planning Dialogue Contributions with New Information Diana Zaiu . . . . . . . . . . . . . . . . . . . . . .. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ~ . . . . . . . . . . . . . . . . . . . . . . . . . . 304

ROMVOX: Text-to-speech synthesis of Romanian (system demo) Licheng Zeng . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 228

•

The Multex Generator and its Environment: Application and Development Dongmo Zhang . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ... 296

MLWFA: Multilingual Weather Forecasting System (system demo) Yujian Zhou 280

Circsum-Tutor: Content Planning in a Tutoring System (system demo) Michael Zock . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58

Automatic Generation of Subway Directions: Salience Gradation as a Factor for Determining Message and Form

Ingrid Zukerman " 148 Attention during Argument Generation and Presentation

xiii

!

• . . , .

! ! !

i|,

. .

. . - . .

. . . .

. • . . •

Xiv

!

!

ill

i | !! .!

i! .!

Papers