When we are interested in a certain domain, we can collect and analyze data from the Internet. The newly collected data is not labeled, so the use of labeled data is hoped to be helpful to the new data. We perform name entity recognition (NER) and aspect-based sentiment analysis (ABSA) in multi-task learning, and combine parameter generation network (Jia et al., 2019) and DANN architecture (Ganin and Lempitsky, 2015) to build the model. In the NER task, the data is labeled with Tie, Break, and the task weight is adjusted according to the loss change rate of each task using Dynamic Weight Average (DWA) (Liu et al., 2019). This study used two different source domain data sets. The experimental results show that Tie, Break can improve the results of the model: DWA can have better performance in the results; the combination of parameter generation network and gradient reversal layer can be used for every good learning in different domain.