arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.06645cs.CL
收藏

使用平行注意联合学习真值-条件表示和背景

Jointly Learning Truth-Conditional Denotations and Groundings using Parallel Attention

UCSD(加州大学圣迭戈分校);ServiceNow(ServiceNow公司);McGill(麦吉尔大学)

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

摘要:

我们提出了一个模型,共同学习的单词的外延连同他们的接地使用真值条件语义。我们的模型建立在Mao等人(2019)的神经符号方法基础上,学习CLEVR数据集中的对象(Johnson等人,2017)使用新颖的并行注意力机制。该模型在视觉问答方面达到了最先进的性能,学习以问题性能作为唯一的训练信号来检测和地面对象。我们还表明,该模型能够通过调整训练集中问题的答案来学习灵活的非规范接地。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑