FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
Citations Over TimeTop 1% of 2018 papers
Abstract
We present a Few-Shot Relation Classification Dataset (FewRel), consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers. The relation of each sentence is first recognized by distant supervision methods, and then filtered by crowdworkers. We adapt the most recent state-of-the-art few-shot learning methods for relation classification and conduct thorough evaluation of these methods. Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans. We also show that a range of different reasoning skills are needed to solve our task. These results indicate that few-shot relation classification remains an open problem and still requires further research. Our detailed analysis points multiple directions for future research. All details and resources about the dataset and baselines are released on http://zhuhao.me/ fewrel.
Related Papers
- → Controllable Processing Times in Project and Production Management: Analysing the Trade-Off between Processing Times and the Amount of Resources(2015)12 cited
- One Shot Device의 저장 신뢰도 분석에 관한 연구(2016)
- → Scientific Relation Extraction with Selectively Incorporated Concept Embeddings(2018)
- Does Use of Steel Shot Result in Greater Waterfowl Crippling? Using Harvest Data to Determine Effectiveness of Non-toxic Shot(2017)
- I've heard that there's a high-dose flu shot available. Is it better for older adults than the regular flu shot? Should I ask for the high-dose shot?(2011)