AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Modelling Form-Meaning Systematicity with Linguistic and Visual Features

Arie Soeteman, Dario Gutierrez, Elia Bruni, Ekaterina Shutova

AAAI 2020 · Vision-language and multimodal › Human and embodied modeling · approach: Layout-aware document understanding · 0 citations (OpenAlex)

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
optimize edit weights (SMLKR) instead of unweighted Levenshtein (ablation)text-based model · form-meaning correlationMantel correlation: 0.0362 -> 0.0383Improved
optimize edit weights instead of unweighted (ablation)image-based model · form-meaning correlationMantel correlation: 0.0198 -> 0.0243Improved
optimize edit weights instead of unweighted (ablation)scoring-level fusion · form-meaning correlationMantel correlation: 0.0401 -> 0.0420Improved
optimize edit weights instead of unweighted (ablation)neural network fusion · form-meaning correlationMantel correlation: 0.0175 -> 0.0266Improved
add visual features via scoring-level fusiontext-based model · form-meaning correlationMantel correlation: 0.0383 -> 0.0420Improved
add visual features via feature concatenationtext-based model · form-meaning correlationMantel correlation: 0.0383 -> 0.0376No clear effect
add visual features via Siamese neural network fusiontext-based model · form-meaning correlationMantel correlation: 0.0383 -> 0.0266Hurt
use image-based vectors instead of text-basedform-meaning model · form-meaning correlationMantel correlation: 0.0383 -> 0.0243Hurt
use image-based instead of text-based vectorsphonaestheme detection · phonaesthemes p < 0.05count: 22 -> 15Hurt
use multimodal concatenation instead of text-basedphonaestheme detection · phonaesthemes p < 0.05count: 22 -> 10Hurt
use neural network fusion instead of text-basedphonaestheme detection · phonaesthemes p < 0.05count: 22 -> 7Hurt
combine text and image distances with alpha (ablation)scoring-level fusion · form-meaning correlationMantel correlation: 0.75Improved

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