Exploration on Generating Traditional Chinese Medicine Prescription from Symptoms with an End-to-End method

TL;DR

This paper introduces an end-to-end seq2seq approach with a novel decoder and loss function for automatically generating Traditional Chinese Medicine prescriptions from symptom descriptions, demonstrating promising results.

Contribution

It proposes a new decoder with coverage and a soft loss function to improve TCM prescription generation using seq2seq models.

Findings

The proposed method reduces repetition issues in sequence generation.

Generated prescriptions received a 7.3 out of 10 rating from TCM experts.

The approach shows potential to assist in real-life TCM prescribing procedures.

Abstract

Traditional Chinese Medicine (TCM) is an influential form of medical treatment in China and surrounding areas. In this paper, we propose a TCM prescription generation task that aims to automatically generate a herbal medicine prescription based on textual symptom descriptions. Sequence-to-sequence (seq2seq) model has been successful in dealing with sequence generation tasks. We explore a potential end-to-end solution to the TCM prescription generation task using seq2seq models. However, experiments show that directly applying seq2seq model leads to unfruitful results due to the repetition problem. To solve the problem, we propose a novel decoder with coverage mechanism and a novel soft loss function. The experimental results demonstrate the effectiveness of the proposed approach. Judged by professors who excel in TCM, the generated prescriptions are rated 7.3 out of 10. It shows that the model can indeed help with the prescribing procedure in real life.