Papers by Jakub Waszczuk
Statistical Parsing of Tree Wrapping Grammars (2020.coling-main)
Copied to clipboard
| Challenge: | Using tree-wrapping grammars, we propose a statistical parsing algorithm for the grammar. |
| Approach: | They propose a statistical parsing algorithm based on neural supertagging and A* parse for Tree-Wrapping Grammars (TWG) they extract a grammar for English from constituency treebanks and discuss first parser results with this grammar. |
| Outcome: | The proposed algorithm is based on neural supertagging and A* parsing. |
Improving Low-resource RRG Parsing with Cross-lingual Self-training (2022.coling-1)
Copied to clipboard
| Challenge: | a theoretical framework for low-resource parsing is understudied in computational linguistics but widely used in typological research . a novel approach uses Role and Reference Grammar to parse low-source languages . |
| Approach: | They propose to extend an existing RRG parser into a cross-lingual parsing model . they also adopt self-training to adapt the model to a related language with no trees . |
| Outcome: | The proposed model extends into a cross-lingual parser, and iteratively expands the training data. |
Contemplata, a Free Platform for Constituency Treebank Annotation (2020.lrec-1)
Copied to clipboard
| Challenge: | Contemplata is dedicated to the annotation of constituency trees. |
| Approach: | They propose to use Contemplata to build treebanks and treebank enrichment with relations between syntactic nodes. |
| Outcome: | The proposed solution is dedicated to the annotation of constituency trees and provides a balanced strategy between automatic parsing and manual revision. |