BriefGPT.xyz
Jun, 2021
预测提及的跨文档指代消解
Cross-document Coreference Resolution over Predicted Mentions
HTML
PDF
Arie Cattan, Alon Eirew, Gabriel Stanovsky, Mandar Joshi, Ido Dagan
TL;DR
该论文介绍了第一个完整的交叉文档代词消解深度学习模型，能够在标注实体和事件时取得很好的效果，并且在预测实体和事件时能够为ECB+数据集设立第一个基准。
Abstract
coreference resolution
has been mostly investigated within a single document scope, showing impressive progress in recent years based on end-to-end models. However, the more challenging task of
cross-document
(CD
→