Few-shot Natural Language Generation for Task-Oriented Dialog
Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Michael Zeng, Jianfeng Gao
Abstract
As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical models typically relies on heavily annotated data, which is infeasible for new domains. Therefore, it is pivotal for an NLG system to generalize well with limited labelled data in real applications.
Topics & Concepts
Dialog boxComputer scienceNatural language generationBenchmark (surveying)Task (project management)Artificial intelligenceNatural language processingDomain (mathematical analysis)Dialog systemSet (abstract data type)Natural languageComponent (thermodynamics)Natural language understandingProgramming languageMathematicsPhysicsManagementMathematical analysisGeodesyGeographyEconomicsThermodynamicsWorld Wide WebTopic ModelingNatural Language Processing TechniquesSpeech and dialogue systems