TY - GEN
T1 - Think visually
T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
AU - Goyal, Ankit
AU - Wang, Jian
AU - Deng, Jia
N1 - Publisher Copyright:
© 2018 Association for Computational Linguistics
PY - 2018
Y1 - 2018
N2 - In this paper, we study the problem of geometric reasoning in the context of question-answering. We introduce Dynamic Spatial Memory Network (DSMN), a new deep network architecture designed for answering questions that admit latent visual representations. DSMN learns to generate and reason over such representations. Further, we propose two synthetic benchmarks, FloorPlanQA and ShapeIntersection, to evaluate the geometric reasoning capability of QA systems. Experimental results validate the effectiveness of our proposed DSMN for visual thinking tasks.
AB - In this paper, we study the problem of geometric reasoning in the context of question-answering. We introduce Dynamic Spatial Memory Network (DSMN), a new deep network architecture designed for answering questions that admit latent visual representations. DSMN learns to generate and reason over such representations. Further, we propose two synthetic benchmarks, FloorPlanQA and ShapeIntersection, to evaluate the geometric reasoning capability of QA systems. Experimental results validate the effectiveness of our proposed DSMN for visual thinking tasks.
UR - http://www.scopus.com/inward/record.url?scp=85063093362&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063093362&partnerID=8YFLogxK
U2 - 10.18653/v1/p18-1242
DO - 10.18653/v1/p18-1242
M3 - Conference contribution
AN - SCOPUS:85063093362
T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 2598
EP - 2608
BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PB - Association for Computational Linguistics (ACL)
Y2 - 15 July 2018 through 20 July 2018
ER -