Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction.
Tianyu GaoXu HanKeyue QiuYuzhuo BaiZhiyu XieYankai LinZhiyuan LiuPeng LiMaosong SunJie ZhouPublished in: CoRR (2021)
Keyphrases
- relation extraction
- weakly supervised
- information extraction
- automatic extraction
- manually annotated
- domain specific
- named entities
- semantic relations
- dependency trees
- learning algorithm
- question answering
- dependency tree
- general purpose
- semantic role labeling
- supervised learning
- broad coverage
- wordnet
- named entity recognition
- knowledge acquisition
- semantic features
- co occurrence
- tree kernels
- feature selection