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: NAACL-HLT (2021)
Keyphrases
- empirical evaluation
- sample size
- human level
- pre trained
- artificial general intelligence
- machine intelligence
- model selection
- intelligent systems
- natural language processing
- web intelligence
- human intelligence
- progressive sampling
- artificial intelligence
- high dimensional
- dimensionality reduction
- upper bound
- training data
- cognitive science
- worst case
- data sets
- ai systems
- feature space
- information extraction
- high dimensionality
- natural language
- cognitive architecture
- reinforcement learning
- machine translation
- cognitive psychology
- image processing
- computer vision
- artificial neural networks