Few-shot Intent Classification and Slot Filling with Retrieved Examples
This addresses the problem of adapting natural language understanding systems to new, resource-scarce domains for developers and researchers, though it is incremental as it builds on retrieval-based methods.
The paper tackles few-shot intent classification and slot filling by proposing a span-level retrieval method with a novel batch-softmax objective, which outperforms previous systems on CLINC and SNIPS benchmarks.
Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain. In this paper, we explore retrieval-based methods for intent classification and slot filling tasks in few-shot settings. Retrieval-based methods make predictions based on labeled examples in the retrieval index that are similar to the input, and thus can adapt to new domains simply by changing the index without having to retrain the model. However, it is non-trivial to apply such methods on tasks with a complex label space like slot filling. To this end, we propose a span-level retrieval method that learns similar contextualized representations for spans with the same label via a novel batch-softmax objective. At inference time, we use the labels of the retrieved spans to construct the final structure with the highest aggregated score. Our method outperforms previous systems in various few-shot settings on the CLINC and SNIPS benchmarks.