태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Given an input sentence, the task is to extract triplets consisting of the head entity, relation label, and tail entity where the relation label is not seen at the training stage.
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
The FewRel (Few-Shot Relation Classification Dataset) contains 100 relations and 70,000 instances from Wikipedia. The dataset is divided into three subsets: training set (64 relations), validation set (16 relations) and test set (20 relations). Source: Neural Snowball for Few-Shot Relation Learning Image Source: https://www.aclweb.org/anthology/D18-1514.pdf
The Wiki-ZSL (Wiki Zero-Shot Learning) dataset contains 113 relations and 94,383 instances from Wikipedia. The dataset is divided into three subsets: training set (98 relations), validation set (5 relations) and test set (10 relations).
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.