@article{Reddy_Rui_Li_Lin_Wen_Cho_Huang_Bansal_Sil_Chang_Schwing_Ji_2022, title={MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding}, volume={36}, url={https://ojs.aaai.org/index.php/AAAI/article/view/21370}, DOI={10.1609/aaai.v36i10.21370}, abstractNote={Recently, there has been an increasing interest in building question answering (QA) models that reason across multiple modalities, such as text and images. However, QA using images is often limited to just picking the answer from a pre-defined set of options. In addition, images in the real world, especially in news, have objects that are co-referential to the text, with complementary information from both modalities. In this paper, we present a new QA evaluation benchmark with 1,384 questions over news articles that require cross-media grounding of objects in images onto text. Specifically, the task involves multi-hop questions that require reasoning over image-caption pairs to identify the grounded visual object being referred to and then predicting a span from the news body text to answer the question. In addition, we introduce a novel multimedia data augmentation framework, based on cross-media knowledge extraction and synthetic question-answer generation, to automatically augment data that can provide weak supervision for this task. We evaluate both pipeline-based and end-to-end pretraining-based multimedia QA models on our benchmark, and show that they achieve promising performance, while considerably lagging behind human performance hence leaving large room for future work on this challenging new task.}, number={10}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Reddy, Revant Gangi and Rui, Xilin and Li, Manling and Lin, Xudong and Wen, Haoyang and Cho, Jaemin and Huang, Lifu and Bansal, Mohit and Sil, Avirup and Chang, Shih-Fu and Schwing, Alexander and Ji, Heng}, year={2022}, month={Jun.}, pages={11200-11208} }