Representation of actions as an interlingua

Authors:
Karin Kipper;Martha Palmer
Affiliations:
University of Pennsylvania, Philadelphia, PA, USA;University of Pennsylvania, Philadelphia, PA, USA
Venue:
NAACL-ANLP-Interlinguas '00 Proceedings of the 2000 NAACL-ANLP Workshop on Applied interlinguas: practical applications of interlingual approaches to NLP - Volume 2
Year:
2000

Citing 7
Cited 1

Machine translation: a view from the Lexicon

Machine translation: a view from the Lexicon
Animation control for real-time virtual humans

Communications of the ACM
Dynamically altering agent behaviors using natural language instructions

AGENTS '00 Proceedings of the fourth international conference on Autonomous agents
Parameterized action representation for virtual human agents

Embodied conversational agents
Class-Based Construction of a Verb Lexicon

Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Synchronous tree-adjoining grammars

COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Preserving semantic dependencies in synchronous Tree Adjoining Grammar

ACL '99 Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics

A multi-path architecture for machine translation of English text into American Sign Language animation

HLT-SRWS '04 Proceedings of the Student Research Workshop at HLT-NAACL 2004

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a Parameterized Action Representation (PAR) that provides a conceptual representation of different types of actions used to animate virtual human agents in a simulated 3D environment. These actions involve changes of state, changes of location (kinematic) and exertion of force (dynamic). PARs are hierarchical, parameterized structures that facilitate both visual and verbal expressions. In order to support the animation of the actions, PARs have tomake explicit many details that are often underspecified in the language. This detailed level of representation also provides a suitable pivot representation for generation in other natural languages, i.e., a form of interlingua. We show examples of how certain divergences in machine translation can be solved by our approach focusing specifically on how verb-framed and satellite-framed languages can use our representation.