Text Genre and Training Data Size in Human-like Parsing.
John B. HaleAdhiguna KuncoroKeith HallChris DyerJonathan BrennanPublished in: EMNLP/IJCNLP (1) (2019)
Keyphrases
- training dataset
- training data
- training set
- training samples
- text mining
- linguistic analysis
- natural language processing
- natural language
- data sets
- web documents
- natural language generation
- text retrieval
- information retrieval
- syntactic analysis
- agent architecture
- classification accuracy
- keywords
- training examples
- test data
- supervised learning
- decision trees
- dependency tree
- test set
- text documents
- semantic network
- domain knowledge
- human robot interaction
- natural language text
- hidden markov models
- syntactic categories