Carsim: A System to Convert Written Accident Reports into Animated 3D Scenes
(2004) Joint SAIS/SSLS Workshop, 2004 p.76-86- Abstract
- This paper describes a system to create animated 3D scenes of car accidents from reports written in Swedish. The system has been developed using news reports of varying size and complexity. The text-to-scene conversion process consists of two stages. An information extraction module creates a tabular description of the accident and a visual simulator generates and animates the scene.
We first describe the overall structure of the text-to-scene conversion and the template structure. We then explain the information extraction and visualization modules. We show snapshots of the car animation output and we conclude with the results we obtained.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/632201
- author
- Johansson, Richard LU ; Nugues, Pierre LU and Williams, David
- organization
- publishing date
- 2004
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- information extraction, Natural language processing, automatic illustration
- host publication
- Proceedings of the 2nd Joint SAIS/SSLS Workshop Artificial Intelligence and Learning Systems, AILS-04
- pages
- 76 - 86
- publisher
- Department of Computer Science, Lund University
- conference name
- Joint SAIS/SSLS Workshop, 2004
- conference location
- Lund, Sweden
- conference dates
- 2004-04-15 - 2004-04-16
- external identifiers
-
- other:LU-CS-TR:2004-230
- language
- English
- LU publication?
- yes
- id
- 226ece86-9e36-4309-9986-56f6c74f435c (old id 632201)
- date added to LUP
- 2016-04-04 11:43:55
- date last changed
- 2021-05-05 16:10:52
@inproceedings{226ece86-9e36-4309-9986-56f6c74f435c, abstract = {{This paper describes a system to create animated 3D scenes of car accidents from reports written in Swedish. The system has been developed using news reports of varying size and complexity. The text-to-scene conversion process consists of two stages. An information extraction module creates a tabular description of the accident and a visual simulator generates and animates the scene.<br/><br> <br/><br> We first describe the overall structure of the text-to-scene conversion and the template structure. We then explain the information extraction and visualization modules. We show snapshots of the car animation output and we conclude with the results we obtained.}}, author = {{Johansson, Richard and Nugues, Pierre and Williams, David}}, booktitle = {{Proceedings of the 2nd Joint SAIS/SSLS Workshop Artificial Intelligence and Learning Systems, AILS-04}}, keywords = {{information extraction; Natural language processing; automatic illustration}}, language = {{eng}}, pages = {{76--86}}, publisher = {{Department of Computer Science, Lund University}}, title = {{Carsim: A System to Convert Written Accident Reports into Animated 3D Scenes}}, year = {{2004}}, }