# Jointly Learning Truth-Conditional Denotations and Groundings using Parallel Attention

Source: [Jointly Learning Truth-Conditional Denotations and Groundings using Parallel Attention](<https://www.sota2.com/research/paper/68fa69b71e209131cea23ad6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:06:39.153Z

Authors: Leon Bergen, Dzmitry Bahdanau, Timothy J. O'Donnell

Published: 2021-04-14T06:33:27.000Z

## Abstract

We present a model that jointly learns the denotations of words together with their groundings using a truth-conditional semantics. Our model builds on the neurosymbolic approach of Mao et al. (2019), learning to ground objects in the CLEVR dataset (Johnson et al., 2017) using a novel parallel attention mechanism. The model achieves state of the art performance on visual question answering, learning to detect and ground objects with question performance as the only training signal. We also show that the model is able to learn flexible non-canonical groundings just by adjusting answers to questions in the training set.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2104.06645>)

[PDF](<https://arxiv.org/pdf/2104.06645.pdf>)
