Lookahead Features
otherentity
ID: lookaheadfeatures
Related Papers
Shift-Reduce Constituent Parsing with Neural Lookahead Features
AbstractTransition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which consists of a …...
Recursive Subtree Composition in LSTM-Based Dependency Parsing
AbstractThe need for tree structure modelling on top of sequence modelling is an open issue in neural dependency parsing. We investigate the impact of adding a tree layer on top …...