MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding release_75pjlfayfzb7hntukwhe4h5wbq

by Revanth Gangi Reddy, Xilin Rui, Manling Li, Xudong Lin, Haoyang Wen, Jaemin Cho, Lifu Huang, Mohit Bansal, Avirup Sil, Shih-Fu Chang, Alexander Schwing, Heng Ji

Released as a article .

2021  

Abstract

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.
In text/plain format

Archived Files and Locations

application/pdf  6.7 MB
file_juswdeearvc5fhfiznbmpnanr4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-12-20
Version   v1
Language   en ?
arXiv  2112.10728v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 744930d8-64f7-45df-8638-9aedfa372a6b
API URL: JSON