Experiments on two lexically constrained text generation datasets and three machine translation datasets demonstrateINSNET's advantages over previous insertion-based methods in terms of training speed,inferenceefficiency,andgenerationquality.

V anilla NA T model assumes that the target tokens are independent of each other given the source sentence. This assumption enables the parallel generation of all tokens.

The generated candidates are novel at both the molecular and chemical scaffold levels when compared to the training data.

Previous works have validated that text generation APIs can be stolen through imitation attacks, causing IP violations. In order to protect the IP of text generationAPIs,recentworkhasintroduced awatermarking algorithm andutilized the null-hypothesis test as a post-hoc ownership verification on the imitation models.