TCMNER and PubMed: A Novel Chinese Character-Level-Based Model and a Dataset for TCM Named Entity Recognition

Table 1

An example of the TCM clinical records.

Item	Content
Clinical manifestation	Insomnia, dreaminess, palpitation, amnesia, dry stool and once every 2 days, wheezing due to retention of phlegm in throat, palms and soles, dysphoria with feverish sensation in chest, tidal fever, night sweating, red tongue, less tongue coating, small and weak pulse
Syndrome	Heart yin injury, the insufficiency of blood and body fluid, hyperactivity of fire due to yin deficiency
Disease	Insomnia
Treatment law	Nourishing yin and the blood, easing mental anxiety
Herbs	Radix Rehmannia preparata, Asparagus cochinchinensis, Radix Scrophulariae, Radix Ginseng, Poria cocos, Chinese angelica, Semen Platycladi, Semen ziziphi spinosae, polygala root, the root of red-rooted salvia, the fruit of Chinese magnolia vine

The main content contains 5 terms: clinical manifestation, syndrome, disease, treatment law, and herbs. Other side information, such as a patient’s name and age, is omitted.