FastRE: Towards Fast Relation Extraction with Convolutional Encoder and Improved Cascade Binary Tagging Framework

by   Guozheng Li, et al.

Recent work for extracting relations from texts has achieved excellent performance. However, most existing methods pay less attention to the efficiency, making it still challenging to quickly extract relations from massive or streaming text data in realistic scenarios. The main efficiency bottleneck is that these methods use a Transformer-based pre-trained language model for encoding, which heavily affects the training speed and inference speed. To address this issue, we propose a fast relation extraction model (FastRE) based on convolutional encoder and improved cascade binary tagging framework. Compared to previous work, FastRE employs several innovations to improve efficiency while also keeping promising performance. Concretely, FastRE adopts a novel convolutional encoder architecture combined with dilated convolution, gated unit and residual connection, which significantly reduces the computation cost of training and inference, while maintaining the satisfactory performance. Moreover, to improve the cascade binary tagging framework, FastRE first introduces a type-relation mapping mechanism to accelerate tagging efficiency and alleviate relation redundancy, and then utilizes a position-dependent adaptive thresholding strategy to obtain higher tagging accuracy and better model generalization. Experimental results demonstrate that FastRE is well balanced between efficiency and performance, and achieves 3-10x training speed, 7-15x inference speed faster, and 1/100 parameters compared to the state-of-the-art models, while the performance is still competitive.


A Hybrid Model of Classification and Generation for Spatial Relation Extraction

Extracting spatial relations from texts is a fundamental task for natura...

Neural Open Relation Extraction via an Overlap-aware Sequence Tagging Scheme

Solving the Open relation extraction (ORE) task with supervised neural n...

Extracting all Aspect-polarity Pairs Jointly in a Text with Relation Extraction Approach

Extracting aspect-polarity pairs from texts is an important task of fine...

Supervised Neural Models Revitalize the Open Relation Extraction

Open relation extraction (ORE) remains a challenge to obtain a semantic ...

LegoNet: A Fast and Exact Unlearning Architecture

Machine unlearning aims to erase the impact of specific training samples...

Global alignment for relation extraction in Microbiology

We investigate a method to extract relations from texts based on global ...

Efficient Encoders for Streaming Sequence Tagging

A naive application of state-of-the-art bidirectional encoders for strea...

Please sign up or login with your details

Forgot password? Click here to reset