Скачать или смотреть text to 3D example

Natural language processing for text comprehension in context requires more than the classification of documents or word sense disambiguation. To understand fiction book sentences, important components of a semantic parsing system must be an inference using general ontology for analyzing successive utterances and the use of background knowledge for objects identification and pragmatic interpretation.

Creating 3D scenes using only natural language can be a challenging task. Animating 3D scenes using natural language adds an additional level of complexity to this task. And yet, over the past 50 years, starting with the pioneering work on the SHRDLU system there were many systems that have attempted to manipulate computer graphics objects using natural language.

In this video we show the current state of our SUMO SRL system. It takes the text of a book and parses it using several parsers, including Stanford CoreNLP and AllenNLP. The parsing results are integrated with the upper SUMO ontology, and finally a simple 3D scene is created.

https://onedrive.live.com/view.aspx?r...

Related GitHub projects

https://github.com/aalgirdas/Procedur...

https://github.com/aalgirdas/novel-se...