What’s The Story

MSC Dissertation

Automatic Extraction of Characters and Scenes from Natural Language Text
A research into a software tool to aid scene designers and modellers to quickly develop scenes and model characters from short stories and scripts by extracting key information from the natural language text.

This project concentrates on the language component of a text-to-scene application. Hence, the entities extracted must contain enough information for the graphic component to successfully render a realistic scene.

Since characters, scenes and objects that populate it are what make a story; these are the entities that are extracted. The characteristics of each entity are extracted to distinguish the entities of the same type from each other. The positioning of characters and objects that populates a scene also need to be extracted for it to be rendered realistically and accurately.

Several natural language processing techniques and packages are tested and evaluated for its accuracy with fiction text before a web application prototype written in Python was created.

Tools & Technologies Used:

  • Eclipse & PyDev
  • Django
  • NLTK
  • Montylingua
  • HTML5
  • PrototypeJS
  • JSON


Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s




%d bloggers like this: