Pre-training to Match for Unified Low-shot Relation Extraction
This addresses low-shot relation extraction for real-world applications where labeled data is scarce, representing a novel unification approach rather than incremental improvement.
The paper tackles the problem of unifying few-shot and zero-shot relation extraction tasks, which require different abilities despite similar goals, by proposing Multi-Choice Matching Networks with triplet-paraphrase meta-training. The method outperforms strong baselines by a large margin and achieves state-of-the-art performance on a few-shot RE leaderboard.
Low-shot relation extraction~(RE) aims to recognize novel relations with very few or even no samples, which is critical in real scenario application. Few-shot and zero-shot RE are two representative low-shot RE tasks, which seem to be with similar target but require totally different underlying abilities. In this paper, we propose Multi-Choice Matching Networks to unify low-shot relation extraction. To fill in the gap between zero-shot and few-shot RE, we propose the triplet-paraphrase meta-training, which leverages triplet paraphrase to pre-train zero-shot label matching ability and uses meta-learning paradigm to learn few-shot instance summarizing ability. Experimental results on three different low-shot RE tasks show that the proposed method outperforms strong baselines by a large margin, and achieve the best performance on few-shot RE leaderboard.