SceneGraphParser
SceneGraphParser copied to clipboard
vacancy
A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).
in backends/spacy_pasrer.py you can modify the line162-163 code as follow: entity.root.head.head.dep_ == 'pobj' and database.is_phrasal_prep(doc[entity.root.head.head.head.i:entity.root.head.i + 1].text.lower())
Hi! FIrst of all I want to thank you for your hard work in developing this library! I am using it to generate graphs from captions, and I noticed that...
> - A fire hydrant pouring water from it with a neon blue glow to it. - Two brown bears growling at each other while laying on a log. -...
Hi, I tried to generate the graph for sentences like ``` a white and red toothbrush a black computer monitor ``` however the parser doesn't work with these sentences. I...
For the sentence "Blond caucasian male in black t-shirt and denim jeans wearing converse sneakers , sitting on a blue foldable chair , an orange box on his lap ."...
hi, can you explain how to regenerate sentences using entitity and relations.
Thanks for the great implementation. Does this function the exact same way as the Stanford Scene Graph Parser? If not, how is it different from the Stanford parser?
``` sng_parser.tprint(sng_parser.parse('the chair is in front of the desk')) Entities: +--------+-----------+-------------+ | Head | Span | Modifiers | |--------+-----------+-------------| | chair | the chair | the | | desk |...
Will this work well for other languages provided I use the appropriate parser? I have tried many non-English languages and no relations are being detected, although the entities look correct....
