We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution. The package is pip-installable, and allows two modes: an accurate mode based on the LingMess architecture, providing state-of-the-art coreference accuracy, and a substantially faster model, F-coref, which is the focus of this work. F-coref allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU (compared to 6 minutes for the LingMess model, and to 12 minutes of the popular AllenNLP coreference model) with only a modest drop in accuracy. The fast speed is achieved through a combination of distillation of a compact model from the LingMess model, and an efficient batching implementation using a technique we call leftover batching. Our code is available at https://github.com/shon-otmazgin/fastcoref

翻译：我们引入了快速、准确和易于使用的英国连带参考分辨率的快速芯片包。 包包是可安装的, 允许两种模式: 一种基于 LingMess 结构的精确模式, 提供最新共同参考准确性, 以及一个大大加快的模型F- 核心f, 这项工作的重点是 F- 核心f。 F- 核心f 允许在 V100 GPU (LingMess 模型为6分钟,流行的 AllenNLP 连带参考模型为12分钟) 上用25秒处理2.8K OntoNotes 文档, 精度略下降。 快速速度是通过合并精炼LingMess 模型的紧凑模型来实现的, 以及使用我们称之为剩余批量的技术高效的分批实施。 我们的代码可以在 https://github. com/shon- otmazgin/fastcoref 上查阅 。