The AI2 system at SemEval-2017 Task 10 (ScienceIE): semi-supervised end-to-end entity and relation extraction.
Waleed AmmarMatthew E. PetersChandra BhagavatulaRussell PowerPublished in: SemEval@ACL (2017)
Keyphrases
- end to end
- relation extraction
- semi supervised
- named entities
- named entity recognition
- entity extraction
- coreference resolution
- named entity recognizer
- information extraction
- artificial intelligence
- unsupervised learning
- weakly supervised
- automatic extraction
- word sense disambiguation
- semantic relations
- semantic role labeling
- dependency trees
- question answering
- co occurrence
- natural language processing
- domain specific
- text mining
- tree kernels
- semantic features
- pairwise
- entity ranking
- knowledge based systems
- expert systems
- labeled data
- active learning
- supervised learning
- text documents
- congestion control
- machine learning
- real world
- feature space
- data mining