ACL 2022long10 citations

Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues

Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Zhongyu Wei

Abstract

It is a common practice for recent works in vision language cross-modal reasoning to adopt a binary or multi-choice classification formulation taking as input a set of source image(s) and textual query. In this work, we take a sober look at such an “unconditional” formulation in the sense that no prior knowledge is specified with respect to the source image(s). Inspired by the designs of both visual commonsense reasoning and natural language inference tasks, we propose a new task termed “Premise-based Multi-modal Reasoning” (PMR) where a textual premise is the background presumption on each source image. The PMR dataset contains 15,360 manually annotated samples which are created by a multi-phase crowd-sourcing process. With selected high-quality movie screenshots and human-curated premise templates from 6 pre-defined categories, we ask crowd-source workers to write one true hypothesis and three distractors (4 choices) given the premise and image through a cross-check procedure.

BibTeX
@inproceedings{dong-etal-2022-premise,
    title = "Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues",
    author = "Dong, Qingxiu  and
      Qin, Ziwei  and
      Xia, Heming  and
      Feng, Tian  and
      Tong, Shoujie  and
      Meng, Haoran  and
      Xu, Lin  and
      Wei, Zhongyu  and
      Zhan, Weidong  and
      Chang, Baobao  and
      Li, Sujian  and
      Liu, Tianyu  and
      Sui, Zhifang",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.66/",
    doi = "10.18653/v1/2022.acl-long.66",
    pages = "932--946"
}
Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues · ACL 2022