Abstract
With the help of pre-trained language models,the accuracy of the entity linking task has made great strides in recent years.However,most models with excellent performance require fine-tuning on a large amount of training data using large pre-trained language models,which is a hardware thresh-old to accomplish this task.Some researchers have achieved competitive results with less training da-ta through ingenious methods,such as utilizing information provided by the named entity recognition model.This paper presents a novel semantic-enhancement-based entity linking approach,named se-mantically enhanced hardware-friendly entity linking(SHEL),which is designed to be hardware friendly and efficient while maintaining good performance.Specifically,SHEL's semantic enhance-ment approach consists of three aspects:(1)semantic compression of entity descriptions using a text summarization model;(2)maximizing the capture of mention contexts using asymmetric heuristics;(3)calculating a fixed size mention representation through pooling operations.These series of seman-tic enhancement methods effectively improve the model's ability to capture semantic information while taking into account the hardware constraints,and significantly improve the model's conver-gence speed by more than 50%compared with the strong baseline model proposed in this paper.In terms of performance,SHEL is comparable to the previous method,with superior performance on six well-established datasets,even though SHEL is trained using a smaller pre-trained language model as the encoder.
基金项目
Beijing Municipal Science and Technology Program(Z231100001323004)
维普
万方数据