F-COREF: Fast, Accurate and Easy to Use Coreference Resolution

• URL: http://arxiv.org/abs/2209.04280v2
• Date: Mon, 12 Sep 2022 09:24:22 GMT
• Title: F-COREF: Fast, Accurate and Easy to Use Coreference Resolution
• Authors: Shon Otmazgin, Arie Cattan, Yoav Goldberg
• Abstract summary: We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution. model allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU.
• Score: 48.05751101475403
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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. \model{} 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. https://github.com/shon-otmazgin/fastcoref

Related papers

• MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm [60.14048367611333]
  MonkeyOCR is a vision-language model for document parsing.<n>It advances the state of the art by leveraging a Structure-Recognition-Relation (SRR) triplet paradigm.
  arXiv  Detail & Related papers  (2025-06-05T16:34:57Z)
• RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation [46.659592045271125]
  RTMO is a one-stage pose estimation framework that seamlessly integrates coordinate classification. It achieves accuracy comparable to top-down methods while maintaining high speed. Our largest model, RTMO-l, attains 74.8% AP on COCO val 2017 and 141 FPS on a single V100 GPU.
  arXiv  Detail & Related papers  (2023-12-12T18:55:29Z)
• Implicit Temporal Modeling with Learnable Alignment for Video Recognition [95.82093301212964]
  We propose a novel Implicit Learnable Alignment (ILA) method, which minimizes the temporal modeling effort while achieving incredibly high performance. ILA achieves a top-1 accuracy of 88.7% on Kinetics-400 with much fewer FLOPs compared with Swin-L and ViViT-H.
  arXiv  Detail & Related papers  (2023-04-20T17:11:01Z)
• TadML: A fast temporal action detection with Mechanics-MLP [0.5148939336441986]
  Temporal Action Detection (TAD) is a crucial but challenging task in video understanding. Most current models adopt both RGB and Optical-Flow streams for the TAD task. We propose a one-stage anchor-free temporal localization method with RGB stream only, in which a novel Newtonian Mechanics-MLP architecture is established.
  arXiv  Detail & Related papers  (2022-06-07T04:07:48Z)
• Block Pruning For Faster Transformers [89.70392810063247]
  We introduce a block pruning approach targeting both small and fast models. We find that this approach learns to prune out full components of the underlying model, such as attention heads.
  arXiv  Detail & Related papers  (2021-09-10T12:46:32Z)
• A Compression-Compilation Framework for On-mobile Real-time BERT Applications [36.54139770775837]
  Transformer-based deep learning models have increasingly demonstrated high accuracy on many natural language processing (NLP) tasks. We propose a compression-compilation co-design framework that can guarantee the identified model to meet both resource and real-time specifications of mobile devices. We present two types of BERT applications on mobile devices: Question Answering (QA) and Text Generation.
  arXiv  Detail & Related papers  (2021-05-30T16:19:11Z)
• FastHand: Fast Hand Pose Estimation From A Monocular Camera [12.790733588554588]
  We propose a fast and accurate framework for hand pose estimation, dubbed as "FastHand" FastHand offers high accuracy scores while reaching a speed of 25 frames per second on an NVIDIA Jetson TX2 graphics processing unit.
  arXiv  Detail & Related papers  (2021-02-14T04:12:41Z)
• Real-Time Execution of Large-scale Language Models on Mobile [49.32610509282623]
  We find the best model structure of BERT for a given computation size to match specific devices. Our framework can guarantee the identified model to meet both resource and real-time specifications of mobile devices. Specifically, our model is 5.2x faster on CPU and 4.1x faster on GPU with 0.5-2% accuracy loss compared with BERT-base.
  arXiv  Detail & Related papers  (2020-09-15T01:59:17Z)
• Faster Person Re-Identification [68.22203008760269]
  We introduce a new solution for fast ReID by formulating a novel Coarse-to-Fine hashing code search strategy. It uses shorter codes to coarsely rank broad matching similarities and longer codes to refine only a few top candidates for more accurate instance ReID. Experimental results on 2 datasets show that our proposed method (CtF) is not only 8% more accurate but also 5x faster than contemporary hashing ReID methods.
  arXiv  Detail & Related papers  (2020-08-16T03:02:49Z)
• TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge [161.4188504786512]
  Real-time semantic video segmentation is a challenging task due to the strict requirements of inference speed. Recent approaches mainly devote great efforts to reducing the model size for high efficiency. We propose a simple and effective framework, dubbed TapLab, to tap into resources from the compressed domain.
  arXiv  Detail & Related papers  (2020-03-30T08:13:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.