Day 19
Section outline
-
May 5th, Monday (16:30-18:30)
Dependency parsing
- Feature extraction, feature functions and feature templates
- Alternative models for dependency parsing: beam search and graph-based dependency parsing
Neural dependency parsing
- Case study: Kiperwasser & Goldberg 2016
- Feature extraction using BiLSTM
- Hinge loss function
Evaluation for dependency parsing
- Unlabelled attachment score (UAS)
- Labelled attachment score (LAS)
References
- Jurafsky and Martin, chapter 19
- Slides from the lecture
- Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations, Kiperwasser and Goldberg, TACL, vol. 4, 2016