Strategies for Generating Coherent Descriptions of Object Movements in Street Scenes

In this chapter a verbalization strategy for the generation of descriptions is motivated which leads to a specific text structure and to an event selection algorithm that is based on a specialization hierarchy of motion verbs. It is assumed that the hearer is familiar with the static parts of the scene and that the system is to inform him about the motions in such a way that he may imagel them. This assumption in turn leads to the strategy of anticipated visualization for the selection of optional deep cases of a verb. Both strategies have been operationalized and are implemented in the NAOS system. It is further shown that the generation of restrictive relative clauses and the use of negation arises naturally from the task of generating referring expressions in a dynamic environment.

[1]  Naoyuki Okada,et al.  Conceptual Taxonomy of Japanese Adjectives for Understanding Natural Language and Picture Patterns , 1980, COLING.

[2]  John B. Carroll,et al.  Language comprehension and the acquisition of knowledge , 1972 .

[3]  R. Schank,et al.  Inside Computer Understanding: Five Programs Plus Miniatures , 1982 .

[4]  Michael Brady,et al.  Computational Models of Discourse , 1983 .

[5]  Gerhard Weber.  Untersuchungen zur mentalen Repräsentation von Bewegungsverben: Merkmale, Dimensionen u. Vorstellungsbilder , 1983 .

[6]  William C. Mann,et al.  Text Generation , 1982, CL.

[7]  Leonard Bolc,et al.  Natural Language Based Computer Systems , 1980 .

[8]  Emmon W. Bach,et al.  Universals in Linguistic Theory , 1970 .

[9]  Hans-Joachim Novak,et al.  A Relational Matching Strategy for Temporal Event Recognition , 1984, GWAI.

[10]  G. Miller,et al.  Language and Perception , 1976 .

[11]  David D. McDonald,et al.  Salience: The Key to the Selection Problem in Natural Language Generation , 1982, ACL.

[12]  Robin N. Campbell,et al.  Recent Advances in the Psychology of Language , 1978 .

[13]  Katharina Morik,et al.  Beyond Domain-Independence: Experience With the Development of a German Language Access System to Highly Diverse Background Systems , 1983, IJCAI.

[14]  Michael Brady,et al.  Natural Language Generation as a Computational Problem: an Introduction , 1983 .

[15]  Antonio Zampolli,et al.  Linguistic structures processing , 1977 .

[16]  Jack Minker,et al.  Logic and Data Bases , 1978, Springer US.

[17]  Kathleen McKeown,et al.  Discourse Strategies for Generating Natural-Language Text , 1985, Artif. Intell..

[18]  Saburo Tsuji,et al.  Understanding a Simple Cartoon Film by a Computer Vision System , 1977, IJCAI.

[19]  Charles J. Fillmore,et al.  THE CASE FOR CASE. , 1967 .

[20]  Raymond Reiter.  On Closed World Data Bases , 1977, Logic and Data Bases.

[21]  Douglas Edmund Appelt,et al.  Planning natural language utterances to satisfy multiple goals , 1981 .

[22]  William C. Mann,et al.  Discourse Structures for Text Generation , 1984, ACL.

[23]  Willem J. M. Levelt,et al.  Structure and use of verbs of motion , 1978 .

[24]  William C. Mann,et al.  Computer Generation of Multiparagraph English Text , 1981, Am. J. Comput. Linguistics.

[25]  John K. Tsotsos,et al.  A framework for visual motion understanding , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Wolfgang Wahlster,et al.  Over-Answering Yes-No Questions: Extended Responses in a NL Interface to a Vision System , 1983, IJCAI.

[27]  Stephan Busemann,et al.  Surface transformations during the generation of written German sentences , 1988 .

[28]  Bernd Neumann,et al.  NOAS: Ein System zur natürlichsprachlichen Beschreibung zeitveränderlicher Szenen , 1986, Inform. Forsch. Entwickl..