Event coreference resolution is an important research problem with many applications. Despite the recent remarkable success of pretrained language models, we argue that it is still highly beneficial to utilize symbolic features for the task. However, as the input for coreference resolution typically comes from upstream components in the information extraction pipeline, the automatically extracted symbolic features can be noisy and contain errors. Also, depending on the specific context, some features can be more informative than others. Motivated by these observations, we propose a novel context-dependent gated module to adaptively control the information flows from the input symbolic features. Combined with a simple noisy training method, our best models achieve state-of-the-art results on two datasets: ACE 2005 and KBP 2016.
翻译：事件关联解答是许多应用中的一个重要研究问题。 尽管经过培训的语言模式最近取得了显著成功,但我们认为,使用象征性的特征来完成这项任务仍然非常有益。然而,由于对共同引用解答的投入通常来自信息提取管道的上游部分,自动提取的符号特征可能很吵而且含有错误。此外,根据具体背景,有些特征可能比其他特征更具有信息性。根据这些观察,我们提出了一个基于背景的新式的封闭模块,以适应性地控制输入符号特征的信息流。加上简单的吵闹培训方法,我们的最佳模型在两个数据集(ACE 2005 和 KBP 2016)上取得了最先进的结果。
相关内容
微信扫码咨询专知VIP会员