Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality.
Adithya V. GanesanMatthew MateroAravind Reddy RavulaHuy VuH. Andrew SchwartzPublished in: CoRR (2021)
Keyphrases
- empirical evaluation
- sample size
- human level
- pre trained
- artificial general intelligence
- machine intelligence
- intelligent systems
- model selection
- natural language processing
- artificial intelligence
- web intelligence
- upper bound
- cognitive science
- training examples
- training data
- human intelligence
- progressive sampling
- information extraction
- high dimensional
- worst case
- ai systems
- feature space
- learning algorithm
- dimensionality reduction