Abstract: An additive supply apparatus includes a cartridge configured to accommodate a liquid additive and discharge the additive through a discharge port thereof, a discharge tube connected to the cartridge and configured to guide the additive discharged from the cartridge, a check valve assembly interposed between the cartridge and the discharge tube and configured to selectively open or close the discharge tube and the discharge port of the cartridge based on a change in pressure, a pump configured to generate the pressure to be provided to the check valve assembly, a pressure tube that connects the pump to the check valve assembly and configured to transmit the pressure to the check valve assembly, and a water supply tube coupled to the discharge tube or the check valve assembly and configured to supply washing water to at least one of the discharge tube or the check valve assembly.

Abstract: There is provided a method for training text-based emotion detection language model. The method comprises receiving text data; generating clean data by removing errors included in the received text data; detecting emotion data related to a specific emotion from the clean data and generating a training dataset including the detected emotion data; and training the language model using the training dataset.