Can We Have Both Fish and Bear's Paw?: Improving Performance, Reliability, and both of them for Relation Extraction under Label Shift.
Yu HongZhixu LiJianfeng QuJiaqing LiangYi LuoMiyu ZhangYanghua XiaoWei WangPublished in: CIKM (2022)
Keyphrases
- relation extraction
- automatic extraction
- information extraction
- named entities
- domain specific
- semantic relations
- semantic role labeling
- question answering
- broad coverage
- semantic features
- dependency trees
- dependency tree
- named entity recognition
- reference resolution
- co occurrence
- tree kernels
- artificial intelligence
- knowledge sources
- document collections
- general purpose
- natural language processing