Generating Long Financial Report using Conditional Variational Autoencoders with Knowledge Distillation

TL;DR

This paper introduces a CVAE-based method with knowledge distillation to generate long financial reports from news, effectively incorporating external background knowledge to improve report quality.

Contribution

It proposes a novel CVAE framework with knowledge distillation for financial report generation, leveraging external news-report data to enhance contextual understanding.

Findings

Outperforms existing methods on BLEU and ROUGE metrics.

Effectively incorporates external knowledge to improve report quality.

Demonstrates superior performance on public datasets.

Abstract

Automatically generating financial report from a piece of news is quite a challenging task. Apparently, the difficulty of this task lies in the lack of sufficient background knowledge to effectively generate long financial report. To address this issue, this paper proposes the conditional variational autoencoders (CVAE) based approach which distills external knowledge from a corpus of news-report data. Particularly, we choose Bi-GRU as the encoder and decoder component of CVAE, and learn the latent variable distribution from input news. A higher level latent variable distribution is learnt from a corpus set of news-report data, respectively extr acted for each input news, to provide background knowledge to previously learnt latent variable distribution. Then, a teacher-student network is employed to distill knowledge to refine theoutput of the decoder component. To evaluate the model performance of the proposed approach, extensive experiments are preformed on a public dataset and two widely adopted evaluation criteria, i.e., BLEU and ROUGE, are chosen in the experiment. The promising experimental results demonstrate that the proposed approach is superior to the rest compared methods.