2021/10/10 by Janarthanan Rajendran, Jonathan K. Kummerfeld, Rajendran, Janarthanan +3
Computer Science · #Computation and Language (cs.CL) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Speech and dialogue systems #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2110.15724
openalex publication_date 2021/10/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
For each goal-oriented dialog task of interest, large amounts of data need to\nbe collected for end-to-end learning of a neural dialog system. Collecting that\ndata is a costly and time-consuming process. Instead, we show that we can use\nonly a small amount of data, supplemented with data from a related dialog task.\nNaively learning from related data fails to improve performance as the related\ndata can be inconsistent with the target task. We describe a meta-learning\nbased method that selectively learns from the related dialog task data. Our\napproach leads to significant accuracy improvements in an example dialog task.\n