Neural Models of Factuality

Neural Models of Factuality
复制标题

DOI:
10.18653/v1/n18-1067
复制
发表时间:
2018-04
期刊:
ArXiv
影响因子:
--
通讯作者:
Rachel Rudinger;Aaron Steven White;Benjamin Van Durme
Rachel Rudinger;Aaron Steven White;Benjamin Van Durme
中科院分区:
其他
文献类型:
--
作者:
Rachel Rudinger;Aaron Steven White;Benjamin Van Durme

文献摘要

被引文献

相似文献

我们提出了两种用于事件真实性预测的神经模型,与之前的模型在三个事件真实性数据集(FactBank、UW 和 MEANTIME)上的性能相比,有了显着的提升。我们还对通用分解语义数据集的发生部分进行了大幅扩展,产生了迄今为止最大的事件事实数据集。我们还报告了这个扩展事实数据集的模型结果。
We present two neural models for event factuality prediction, which yield significant performance gains over previous models on three event factuality datasets: FactBank, UW, and MEANTIME. We also present a substantial expansion of the It Happened portion of the Universal Decompositional Semantics dataset, yielding the largest event factuality dataset to date. We report model results on this extended factuality dataset as well.