论文标题
F-Coref：快速，准确且易于使用的核心分辨率
F-coref: Fast, Accurate and Easy to Use Coreference Resolution
论文作者
论文摘要
我们介绍了FastCoref，这是一个用于快速，准确且易于使用的英语核心分辨率的Python软件包。该软件包是可以安装的，并且允许两种模式：基于LingMess体系结构的精确模式，提供最新的核心精度，以及基本更快的模型F-Coref，这是本工作的重点。 F-COREF允许在V100 GPU上25秒内处理2.8K Ontonotes文档（相比之下，LingMess模型为6分钟，而流行的AllennLP Coreference模型的12分钟）仅适度降低精度。快速的速度是通过使用我们称为“剩余批处理”的技术的技术来实现紧凑模型的蒸馏以及有效的批处理实现实现的。我们的代码可在https://github.com/shon-otmazgin/fastcoref上找到
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
