A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss
This work addresses the problem of low diversity in dialogue responses for AI systems, but it is incremental as it builds on existing methods with limited gains.
The study investigated whether adding a semantic loss objective to generative dialogue models improves response diversity, finding it enhanced diversity on a smaller dataset (Frames) but performed similarly to standard training on a larger dataset (MultiWoZ).
Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training objectives do not foster generating alternate responses to a context. But, the effects of minimizing an alternate training objective that fosters a model to generate alternate response and score it on semantic similarity has not been well studied. We hypothesize that a language generation model can improve on its diversity by learning to generate alternate text during training and minimizing a semantic loss as an auxiliary objective. We explore this idea on two different sized data sets on the task of next utterance generation in goal oriented dialogues. We make two observations (1) minimizing a semantic objective improved diversity in responses in the smaller data set (Frames) but only as-good-as minimizing the NLL in the larger data set (MultiWoZ) (2) large language model embeddings can be more useful as a semantic loss objective than as initialization for token embeddings.