Zero-Shot Learning for Joint Intent and Slot Labeling
This addresses the challenge of scaling NLU components for real-world tasks with many intents and slots, though it is incremental as it extends zero-shot methods from slot labeling to joint tasks.
The paper tackles the problem of expensive annotation for joint intent and slot labeling in task-oriented dialog systems by proposing a zero-shot learning approach that requires no labeled examples, showing substantial improvements over strong baselines.
It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Language Understanding (NLU) components of task-oriented dialog systems, especially for the many real world tasks that have a large and growing number of intents and slot types. While zero shot learning approaches that require no labeled examples -- only features and auxiliary information -- have been proposed only for slot labeling, we show that one can profitably perform joint zero-shot intent classification and slot labeling. We demonstrate the value of capturing dependencies between intents and slots, and between different slots in an utterance in the zero shot setting. We describe NN architectures that translate between word and sentence embedding spaces, and demonstrate that these modifications are required to enable zero shot learning for this task. We show a substantial improvement over strong baselines and explain the intuition behind each architectural modification through visualizations and ablation studies.