Advertisement

AQuA: ASP-Based Visual Question Answering

  • Kinjal BasuEmail author
  • Farhad Shakerin
  • Gopal Gupta
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12007)

Abstract

AQuA (ASP-based Question Answering) is an Answer Set Programming (ASP) based visual question answering framework that truly “understands” an input picture and answers natural language questions about that picture. The knowledge contained in the picture is extracted using YOLO, a neural network-based object detection technique, and represented as an answer set program. Natural language processing is performed on the question to transform it into an ASP query. Semantic relations are extracted in the process for deeper understanding and to answer more complex questions. The resulting knowledge-base—with additional commonsense knowledge imported—can be used to perform reasoning using an ASP system, allowing it to answer questions about the picture, just like a human. This framework achieves 93.7% accuracy on CLEVR dataset, which exceeds human baseline performance. What is significant is that AQuA translates a question into an ASP query without requiring any training. Our framework for Visual Question Answering is quite general and closely simulates the way humans operate. In contrast to existing purely machine learning-based methods, our framework provides an explanation for the answer it computes, while maintaining high accuracy.

Keywords

Answer set programming Visual question answering Commonsense reasoning Natural language understanding 

Notes

Acknowledgement

We are indebted to Dhruva Pendharkar for his early work on natural language question answering. Thanks also to Sarat Varanasi for discussion and help. Authors gratefully acknowledge support from NSF grants IIS 1910131 and IIS 1718945.

References

  1. 1.
    Cao, Q., Liang, X., Li, B., Li, G., Lin, L.: Visual question reasoning on general dependency tree. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7249–7257 (2018)Google Scholar
  2. 2.
    Davidson, D.: Inquiries into Truth and Interpretation: Philosophical Essays, vol. 2. Oxford University Press, Oxford (2001)CrossRefGoogle Scholar
  3. 3.
    Gao, H., Mao, J., Zhou, J., Huang, Z., Wang, L., Xu, W.: Are you talking to a machine? Dataset and methods for multilingual image question. In: NIPS 2015, pp. 2296–2304 (2015)Google Scholar
  4. 4.
    Gelfond, M., Kahl, Y.: Knowledge Representation, Reasoning, and the Design of Intelligent Agents: The Answer-Set Programming Approach. Cambridge University Press, Cambridge (2014)CrossRefGoogle Scholar
  5. 5.
    Gelfond, M., Lifschitz, V.: The stable model semantics for logic programming. In: ICLP/SLP, vol. 88, pp. 1070–1080 (1988)Google Scholar
  6. 6.
    Honnibal, M., Montani, I.: spaCy 2: natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. 7 (2017, to appear)Google Scholar
  7. 7.
    Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko, K.: Learning to reason: end-to-end module networks for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 804–813 (2017)Google Scholar
  8. 8.
    Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. arXiv preprint arXiv:1803.03067 (2018)
  9. 9.
    Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: IEEE CVPR 2017, pp. 2901–2910 (2017)Google Scholar
  10. 10.
    Johnson, J., et al.: Inferring and executing programs for visual reasoning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2989–2998 (2017)Google Scholar
  11. 11.
    Joshi, V., Peters, M., Hopkins, M.: Extending a parser to distant domains using a few dozen partially annotated examples. arXiv preprint arXiv:1805.06556 (2018)
  12. 12.
    Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32–73 (2017)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. In: NIPS 2014, pp. 1682–1690 (2014)Google Scholar
  14. 14.
    Manning, C.D., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S.J., McClosky, D.: The Stanford CoreNLP natural language processing toolkit. In: ACL System Demonstrations, pp. 55–60 (2014)Google Scholar
  15. 15.
    Marple, K., Salazar, E., Gupta, G.: Computing stable models of normal logic programs without grounding. arXiv:1709.00501 (2017)
  16. 16.
    Mascharka, D., Tran, P., Soklaski, R., Majumdar, A.: Transparency by design: closing the gap between performance and interpretability in visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4942–4950 (2018)Google Scholar
  17. 17.
    Miller, G.A.: WordNet: a lexical database for english. Commun. ACM 38(11), 39–41 (1995).  https://doi.org/10.1145/219717.219748CrossRefGoogle Scholar
  18. 18.
    Pendharkar, D., Gupta, G.: An ASP based approach to answering questions for natural language text. In: Alferes, J.J., Johansson, M. (eds.) PADL 2019. LNCS, vol. 11372, pp. 46–63. Springer, Cham (2019).  https://doi.org/10.1007/978-3-030-05998-9_4CrossRefGoogle Scholar
  19. 19.
    Perez, E., et al.: FiLM: visual reasoning with a general conditioning layer. In: AAAI (2018)Google Scholar
  20. 20.
    Redmon, J., Divvala, S.K., Girshick, R.B., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR, pp. 779–788. IEEE Computer Society (2016)Google Scholar
  21. 21.
    Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
  22. 22.
    Ren, M., Kiros, R., Zemel, R.: Exploring models and data for image question answering. In: NIPS 2015, pp. 2953–2961 (2015)Google Scholar
  23. 23.
    Santor, A., et al.: A simple neural network module for relational reasoning. In: NIPS 2017, pp. 4967–4976 (2017)Google Scholar
  24. 24.
    Schuster, S., Manning, C.D.: Enhanced English universal dependencies: an improved representation for natural language understanding tasks. In: LRED 2016, pp. 2371–2378 (2016)Google Scholar
  25. 25.
    Shah, S., Mishra, A., Yadati, N., Talukdar, P.P.: KVQA: knowledge-aware visual question answering. In: AAAI (2019)Google Scholar
  26. 26.
    Shakerin, F., Salazar, E., Gupta, G.: A new algorithm to automate inductive learning of default theories. TPLP 17(5–6), 1010–1026 (2017)MathSciNetzbMATHGoogle Scholar
  27. 27.
    Shrestha, R., Kafle, K., Kanan, C.: Answer them all! Toward universal visual question answering models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10472–10481 (2019)Google Scholar
  28. 28.
    Speer, R., Chin, J., Havasi, C.: ConceptNet 5.5: an open multilingual graph of general knowledge. In: Proceedings AAAI, pp. 4444–4451 (2017)Google Scholar
  29. 29.
    Suarez, J., Johnson, J., Li, F.F.: DDRprog: a CLEVR differentiable dynamic reasoning programmer. arXiv preprint arXiv:1803.11361 (2018)
  30. 30.
    Wu, Q., Teney, D., Wang, P., Shen, C., Dick, A., van den Hengel, A.: Visual question answering: a survey of methods and datasets. Comput. Vis. Image Underst. 163, 21–40 (2017)CrossRefGoogle Scholar
  31. 31.
    Yang, Z., He, X., Gao, J., Deng, L., Smola, A.J.: Stacked attention networks for image question answering. CVPR, pp. 21–29 (2015)Google Scholar
  32. 32.
    Yi, K., et al.: Neural-symbolic VQA: disentangling reasoning from vision and language understanding. In: NIPS 2018, pp. 1031–1042 (2018)Google Scholar
  33. 33.
    Yu, L., Park, E., Berg, A.C., Berg, T.L.: Visual madlibs: fill in the blank image generation and question answering. arXiv preprint arXiv:1506.00278 (2015)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.The University of Texas at DallasRichardsonUSA

Personalised recommendations