Few-shot Slot Filling and Intent Classification with Retrieved Examples
Abstract
Few-shot learning is an important problem in natural language understanding tasks due to scenarios such as inclusion of new domains and labels. In this paper, we explore retrieval-based methods for tackling the few-shot intent classification and slot filling tasks due to their advantage of 1) better adaptation to new domains; and 2) not requiring model retraining with new labels.
However, structured prediction beyond intent classification is challenging for retrieval-based methods. In this work, we propose a span-level retrieval method by learning similar contextualized representations for spans with the same label. At inference time, we use the labels of the retrieved spans to construct the final structure. We show that our method outperforms previous systems in the few-shot setting on the CLINC and SNIPS benchmarks.
However, structured prediction beyond intent classification is challenging for retrieval-based methods. In this work, we propose a span-level retrieval method by learning similar contextualized representations for spans with the same label. At inference time, we use the labels of the retrieved spans to construct the final structure. We show that our method outperforms previous systems in the few-shot setting on the CLINC and SNIPS benchmarks.
Research Areas
