arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.02174cs.CLcs.AIcs.LG
收藏

CompGuessWhat?!:基于多任务的语言学习评价框架

CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning

Heriot-Watt University(赫瑞-瓦特大学);University of Copenhagen(哥本哈根大学);University of Edinburgh(爱丁堡大学)

Alessandro Suglia, Ioannis Konstas, Andrea Vanzo, Emanuele Bastianelli, Desmond Elliott, Stella Frank, Oliver Lemon

摘要:

接地语言学习的方法通常集中在一个单一的基于任务的最终性能指标,可能不依赖于所学习的隐藏表征的理想属性,如预测突出属性或概括看不见的情况的能力。为了解决这个问题,我们提出了GROLLA,一个基于属性的语言学习的评估框架,它有三个子任务:1)目标导向的评估; 2)对象属性预测评估; 3)Zero-shot评估。我们还提出了一个新的数据集CompGuessWhat?!作为该框架的一个实例,用于评估学习的神经表征的质量,特别是关于属性基础。为此,我们扩展了原来的GuessWhat?!通过在感知层之上包括语义层来实现数据集。具体来说,我们丰富了与GuessWhat?!具有抽象和情境属性的图像。通过使用诊断分类器,我们表明,目前的模型学习的表示是不够的表达编码对象属性(平均F1为44.27)。此外,当游戏中涉及到新的场景或物体时,他们不会学习足够强大的策略或表示(zero-shot最佳准确率为50.06%)。

英文摘要:

Approaches to Grounded Language Learning typically focus on a single task-based final performance measure that may not depend on desirable properties of the learned hidden representations, such as their ability to predict salient attributes or to generalise to unseen situations. To remedy this, we present GROLLA, an evaluation framework for Grounded Language Learning with Attributes with three sub-tasks: 1) Goal-oriented evaluation; 2) Object attribute prediction evaluation; and 3) Zero-shot evaluation. We also propose a new dataset CompGuessWhat?! as an instance of this framework for evaluating the quality of learned neural representations, in particular concerning attribute grounding. To this end, we extend the original GuessWhat?! dataset by including a semantic layer on top of the perceptual one. Specifically, we enrich the VisualGenome scene graphs associated with the GuessWhat?! images with abstract and situated attributes. By using diagnostic classifiers, we show that current models learn representations that are not expressive enough to encode object attributes (average F1 of 44.27). In addition, they do not learn strategies nor representations that are robust enough to perform well when novel scenes or objects are involved in gameplay (zero-shot best accuracy 50.06%).

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。

↑