search

DreamInvoker / GAIN

Source code for EMNLP 2020 paper: Double Graph Based Reasoning for Document-level Relation Extraction
MIT License
142 stars 31 forks source link

Spatial features? #21

Open alejandrojcastaneira opened 3 years ago

alejandrojcastaneira commented 3 years ago

I was wondering if maybe it would be possible to apply the GAIN framework on document images.

Perhaps, could we include spatial features like the position (x, y) of each entity, along with other features that are used in the model like the text embeddings, entity type embeddings, etc.?

logan-markewich commented 3 years ago

Probably! You could add the spatial features to the representation of each entity maybe and see what happens?

Datasets like DAD or PubLayNet provide information about the location and category of blocks of text.