AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

QUAREL: A Dataset and Models for Answering Questions about Qualitative Relationships

Oyvind Tafjord, Peter Clark, Matt Gardner, Wen-tau Yih, Ashish Sabharwal

AAAI 2019 · Vision-language and multimodal › Visual question answering · approach: Open-domain multimodal QA

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add world mention identification and delexicalization (ablation)QuaSP · QuaRel testanswer accuracy: 56.1 -> 68.7Improved
Add world mention identification and delexicalization (ablation)QuaSP · QuaRel^F testanswer accuracy: 61.7 -> 74.5Improved
Add world mention identification and delexicalization (ablation)QuaSP · QuaRel testparse accuracy: 32.2 -> 43.8Improved
Add world mention identification and delexicalization (ablation)QuaSP · QuaRel^F testparse accuracy: 43.2 -> 59.0Improved
Use property-to-token entity-linking scores and property word lists for unseen propertiesQuaSP+Zero · QuaRel^F unseen-property testanswer accuracy: 50.0 -> 61.0Improved
Use property-to-token entity-linking scores and property word lists for unseen propertiesQuaSP+Zero · QuaRel unseen-property testanswer accuracy: 50.0 -> 59.5%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy