S2ynRE: Two-stage Self-training with Synthetic data for Low-resource Relation Extraction.
Benfeng XuQuan WangYajuan LyuDai DaiYongdong ZhangZhendong MaoPublished in: ACL (1) (2023)
Keyphrases
- synthetic data
- relation extraction
- automatic extraction
- information extraction
- domain specific
- named entities
- dependency tree
- broad coverage
- semantic role labeling
- semantic features
- semantic relations
- real world
- question answering
- named entity recognition
- real image data
- reference resolution
- dependency trees
- data sets
- tree kernels
- general purpose
- semi supervised
- semi supervised learning
- training set
- unsupervised learning
- natural language processing
- text mining
- parse tree
- object recognition
- co occurrence
- natural language
- semantic information
- information retrieval
- markov random field
- named entity recognizer