F-coref: Fast, Accurate and Easy to Use Coreference Resolution
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
Code (1)
Tasks
coreference-resolutionCoreference ResolutionGPUMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Exploring Span Representations in Neural Coreference Resolution
In coreference resolution, span representations play a key role to predict coreference links accurately. We present a thorough examination of the span representation derived by applying BERT on coreference resolution (Jo…
coreference-resolutionCoreference ResolutionD-Coref: A Fast and Lightweight Coreference Resolution Model using DistilBERT
Smart devices are often deployed in some edge-devices, which require quality solutions in limited amount of memory usage. In most of the user-interaction based smart devices, coreference resolution is often required. Kee…
coreference-resolutionCoreference ResolutionEasy-first Coreference Resolution
Easy Victories and Uphill Battles in Coreference Resolution
ezCoref: A Scalable Approach for Collecting Crowdsourced Annotations for Coreference Resolution
Large-scale high-quality corpora are critical for advancing research in coreference resolution. Coreference annotation is typically time consuming and expensive, since researchers generally hire expert annotators and tra…
coreference-resolutionCoreference Resolution