arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.08274cs.CL
收藏

非神经模型的重要性:对神经指称表达生成系统的重新评估

Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systems

University of Cologne(科隆大学);Utrecht University(乌得勒支大学)

Fahime Same, Guanyi Chen, Kees van Deemter

摘要:

近年来,神经模型在NLG中的表现往往优于基于规则的和经典的机器学习方法。这些经典方法现在经常被忽视,例如在评估新的神经模型时。我们认为,它们不应该被忽视,因为对于某些任务,设计良好的非神经方法比神经方法实现更好的性能。本文以生成语言语境中的指称表达为例,对指称表达的生成过程进行了研究。我们检查了两个非常不同的英语数据集(WEBNLG和WSJ),并使用自动和人工评估来评估每个算法。总的来说,这些评估的结果表明,与最先进的神经REG系统相比,具有简单规则集的基于规则的系统在两个数据集上都实现了同等或更好的性能。在更真实的数据集,WSJ,一个基于机器学习的系统,具有精心设计的语言特征,表现最好。我们希望我们的工作可以鼓励研究人员在未来考虑非神经模型。

英文摘要:

In recent years, neural models have often outperformed rule-based and classic Machine Learning approaches in NLG. These classic approaches are now often disregarded, for example when new neural models are evaluated. We argue that they should not be overlooked, since, for some tasks, well-designed non-neural approaches achieve better performance than neural ones. In this paper, the task of generating referring expressions in linguistic context is used as an example. We examined two very different English datasets (WEBNLG and WSJ), and evaluated each algorithm using both automatic and human evaluations. Overall, the results of these evaluations suggest that rule-based systems with simple rule sets achieve on-par or better performance on both datasets compared to state-of-the-art neural REG systems. In the case of the more realistic dataset, WSJ, a machine learning-based system with well-designed linguistic features performed best. We hope that our work can encourage researchers to consider non-neural models in future.

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。

↑