Open Information Extraction (OpenIE) has been used in the pipelines of various NLP tasks. Unfortunately, there is no clear consensus on which models to use in which tasks. Muddying things further is the lack of comparisons that take differing training sets into account. In this paper, we present an application-focused empirical survey of neural OpenIE models, training sets, and benchmarks in an effort to help users choose the most suitable OpenIE systems for their applications. We find that the different assumptions made by different models and datasets have a statistically significant effect on performance, making it important to choose the most appropriate model for one's applications. We demonstrate the applicability of our recommendations on a downstream Complex QA application.
翻译:开放信息提取系统(OpenIE)被应用于各种国家实验室方案任务的管道中。 不幸的是,对于在哪些模式中使用哪些任务并没有明确的共识。 更糟糕的是,缺乏考虑到不同培训组合的比较。 在本文中,我们介绍了对神经开放信息模型、培训组合和基准的以应用为重点的实证调查,以帮助用户选择最适合其应用的系统。我们发现,不同模型和数据集的不同假设对业绩具有统计上的重大影响,因此必须选择最适合个人应用的模式。 我们展示了我们对下游复杂QA应用的建议的适用性。