Non-Sample Equilibrium Fine-grained Financial Element Extraction
Financial element extraction attempts to utilize information extraction technology to extract particular enti-ties and phrases from contracts and plans that can reflect the main information of financial documents.This task is challenged by long tail distribution of samples,fine granularity,long components and long text,which are seldom encountered in other extraction work.The model ENAPtBERT is proposed in this research to convert the factor ex-traction job into a prediction task using typed head and tail pointers.The ENAPtBERT head and tail pointer's design reduces the impact of unlawful labels and may solve the imbalance issue by combining the imbalanced loss function.Meanwhile,the ENAPtBERT improves the accuracy of element finding and categorization by using the newly added element name information.Experiments indicate that the proposed method achieves 2.50％increase in Micro-F1 and 2.66％increase in Macro-F1 when compared to the existing methods.
financial element extractionimbalancefine-grainedelement name information
万方数据
维普
