DistALANER: Distantly Supervised Active Learning Augmented Named Entity Recognition in the Open Source Software Ecosystem.
Somnath BanerjeeAvik DuttaAaditya AgrawalRima HazraAnimesh MukherjeePublished in: CoRR (2024)
Keyphrases
- open source software
- named entity recognition
- semi supervised
- active learning
- open source
- supervised learning
- labeled data
- learning algorithm
- open source software development
- sequence labeling
- text summarization
- source code
- unsupervised learning
- named entities
- open source projects
- relation extraction
- software development
- information extraction
- annotated corpus
- pairwise
- classifier ensemble
- free software
- machine learning
- maintenance effort
- weakly supervised
- training set
- information retrieval
- maximum entropy
- relevance feedback
- natural language processing
- mailing lists
- learning process
- natural language
- conditional random fields
- generative model