CLEVR Parser: A Graph Parser Library for Geometric Learning on Language Grounded Image Scenes

Published in 2nd Workshop for Natural Language Processing Open Source Software (NLP-OSS) , EMNLP-2020, Virtual Event, 2020


  • Link to paper.
  • Link to homepage of Natural Language Processing Open Source Software (NLP-OSS) Workshop, EMNLP 2020.


The CLEVR dataset has been used extensively in language grounded visual reasoning in Machine Learning (ML) and Natural Language Processing (NLP) domains. We present a graph parser library for CLEVR, that provides functionalities for object-centric attributes and relationships extraction, and con- struction of structural graph representations for dual modalities. Structural order-invariant representations enable geometric learning and can aid in downstream tasks like language grounding to vision, robotics, compositionality, interpretability, and computational grammar construction. We provide three extensible main components – parser, embedder, and visualizer that can be tailored to suit specific learning setups. We also provide out-of-the-box functionality for seamless integration with popular deep graph neural network (GNN) libraries. Additionally, we discuss downstream usage and applications of the library, and how it accelerates research for the NLP research community.