Generating Long Financial Report using Conditional Variational Autoencoders with Knowledge Distillation
This work addresses a domain-specific problem for financial analysis by generating reports from news, but it is incremental as it builds on existing CVAE and knowledge distillation techniques.
The paper tackled generating long financial reports from news by addressing the lack of background knowledge, using a conditional variational autoencoder with knowledge distillation, and achieved superior results on BLEU and ROUGE metrics compared to other methods.
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.