Adversarial Bootstrapping for Multi-Turn Dialogue Model Training

Systems described herein may use machine classifiers to perform a variety of natural language understanding tasks including, but not limited to multi-turn dialogue generation. Machine classifiers in accordance with aspects of the disclosure may model multi-turn dialogue as a one-to-many prediction task. The machine classifier may be trained using adversarial bootstrapping between a generator and a discriminator with multi-turn capabilities. The machine classifiers may be trained in both auto-regressive and traditional teacher-forcing modes, with the maximum likelihood loss of the auto-regressive outputs being weighted by the score from a metric-based discriminator model. The discriminators input may include a mixture of ground truth labels, the teacher-forcing outputs of the generator, and/or negative examples from the dataset. This mixture of input may allow for richer feedback on the autoregressive outputs of the generator. Additionally, dual sampling may improve response relevance and coherence by overcoming the problem of exposure bias.