Measuring Societal Biases from Text Corpora with Smoothed First-Order Co-occurrence.
Navid RekabsazRobert WestJames HendersonAllan HanburyPublished in: ICWSM (2021)
Keyphrases
- co occurrence
- text corpora
- topic models
- concept hierarchy
- text corpus
- text mining
- topic modeling
- wordnet
- text analysis
- computational linguistics
- text documents
- document collections
- semantic relations
- semantic similarity
- latent dirichlet allocation
- named entities
- text classifiers
- latent semantic analysis
- probabilistic latent semantic analysis
- text collections
- knowledge base
- text retrieval
- text classification
- domain specific
- information extraction