English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

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

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