SkillNet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach
This addresses the challenge of efficient multi-task learning in natural language generation for AI practitioners, though it is incremental as it builds on sparsely activated and multi-task learning paradigms.
The paper tackles the problem of handling multiple natural language generation tasks with a single model by introducing SkillNet-NLG, a sparsely activated approach that selectively activates parameters based on predefined skills, and it outperforms previous methods on four out of five Chinese NLG tasks while achieving comparable performance to task-specific models.
We present SkillNet-NLG, a sparsely activated approach that handles many natural language generation tasks with one model. Different from traditional dense models that always activate all the parameters, SkillNet-NLG selectively activates relevant parts of the parameters to accomplish a task, where the relevance is controlled by a set of predefined skills. The strength of such model design is that it provides an opportunity to precisely adapt relevant skills to learn new tasks effectively. We evaluate on Chinese natural language generation tasks. Results show that, with only one model file, SkillNet-NLG outperforms previous best performance methods on four of five tasks. SkillNet-NLG performs better than two multi-task learning baselines (a dense model and a Mixture-of-Expert model) and achieves comparable performance to task-specific models. Lastly, SkillNet-NLG surpasses baseline systems when being adapted to new tasks.