MTLB-STRUCT @PARSEME 2020: Capturing Unseen Multiword Expressions Using Multi-task Learning and Pre-trained Masked Language Models.
Shiva TaslimipoorSara BahaadiniEkaterina KochmarPublished in: CoRR (2020)
Keyphrases
- language model
- multiword
- multi task
- learning tasks
- context sensitive
- probabilistic model
- n gram
- information retrieval
- training examples
- natural language
- retrieval model
- transfer learning
- learning problems
- document representation
- feature selection
- training set
- training data
- vector space model
- learning algorithm
- metric learning
- bayesian networks
- neural network