A Sequence Tagging based Framework for Few-Shot Relation Extraction
This addresses the challenge of relation extraction for domains lacking sufficient labeled data, though it is incremental as it adapts existing sequence tagging methods.
The paper tackles the problem of relation extraction in domains with limited labeled data by proposing a few-shot RE framework based on sequence tagging, achieving solid results on two few-shot tasks constructed from a public dataset.
Relation Extraction (RE) refers to extracting the relation triples in the input text. Existing neural work based systems for RE rely heavily on manually labeled training data, but there are still a lot of domains where sufficient labeled data does not exist. Inspired by the distance-based few-shot named entity recognition methods, we put forward the definition of the few-shot RE task based on the sequence tagging joint extraction approaches, and propose a few-shot RE framework for the task. Besides, we apply two actual sequence tagging models to our framework (called Few-shot TPLinker and Few-shot BiTT), and achieves solid results on two few-shot RE tasks constructed from a public dataset.