Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark.
Guanhua ZhangBing BaiJian LiangKun BaiConghui ZhuTiejun ZhaoPublished in: CoRR (2020)
Keyphrases
- natural language
- knowledge representation
- benchmark datasets
- quantitative evaluation
- bayesian inference
- probabilistic inference
- neural network
- natural language interface
- efficient learning
- random fields
- feature set
- natural language processing
- real life
- bayesian networks
- knowledge base
- information extraction
- expert systems
- synthetic datasets
- bayesian model
- search engine
- natural language generation
- grammatical inference
- database
- formal language