arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09788cs.CLcs.AIcs.NE
收藏

从前提中可视化地生成蕴涵

Visuallly Grounded Generation of Entailments from Premises

IRISA(法国信息与随机系统研究所);Université de Rennes I(雷恩第一大学);Institute of Linguistics and Language Technology, University of Malta(马耳他大学语言学与语言技术研究所)

Somaye Jafaritazehjani, Albert Gatt, Marc Tanti

摘要:

自然语言推理是确定前提和假设之间的语义关系的任务。在本文中,我们专注于{ \em代}的假设前提在多模态设置,生成一个句子(假设)给定的图像和/或其描述(前提)作为输入。本文的主要目标是:(a)调查是否是合理的框架NLI作为一个生成任务;(b)考虑在何种程度上接地文本前提的视觉信息是有益的生成。我们比较了不同的神经架构,通过自动和人工评估表明,蕴涵确实可以成功生成。我们还表明,多模态模型优于单峰模型在这项任务中,虽然微不足道。

英文摘要:

Natural Language Inference (NLI) is the task of determining the semantic relationship between a premise and a hypothesis. In this paper, we focus on the {\em generation} of hypotheses from premises in a multimodal setting, to generate a sentence (hypothesis) given an image and/or its description (premise) as the input. The main goals of this paper are (a) to investigate whether it is reasonable to frame NLI as a generation task; and (b) to consider the degree to which grounding textual premises in visual information is beneficial to generation. We compare different neural architectures, showing through automatic and human evaluation that entailments can indeed be generated successfully. We also show that multimodal models outperform unimodal models in this task, albeit marginally.

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。

↑