Stress Test Evaluation for Natural Language Inference.
Aakanksha NaikAbhilasha RavichanderNorman M. SadehCarolyn Penstein RoséGraham NeubigPublished in: CoRR (2018)
Keyphrases
- natural language
- evaluation method
- machine learning
- evaluation model
- gold standard
- bayesian inference
- semantic representation
- knowledge representation
- inference process
- databases
- evaluation methods
- semantic analysis
- test data
- information retrieval systems
- markov random field
- information extraction
- bayesian networks
- information systems
- computer vision
- social networks
- genetic algorithm