Hei Lo | The Chinese University of Hong Kong (original) (raw)
Related Authors
The Chinese University of Hong Kong
Uploads
Papers by Hei Lo
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
We introduce a data-driven approach to generating derivation trees from meaning representation gr... more We introduce a data-driven approach to generating derivation trees from meaning representation graphs with probabilistic synchronous hyperedge replacement grammar (PSHRG). SHRG has been used to produce meaning representation graphs from texts and syntax trees, but little is known about its viability on the reverse. In particular, we experiment on Dependency Minimal Recursion Semantics (DMRS) and adapt PSHRG as a formalism that approximates the semantic composition of DMRS graphs and simultaneously recovers the derivations that license the DMRS graphs. Consistent results are obtained as evaluated on a collection of annotated corpora. This work reveals the ability of PSHRG in formalizing a syntaxsemantics interface, modelling compositional graph-to-tree translations, and channelling explainability to surface realization.
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning, 2019
This paper describes our system (RE-SOLVER) submitted to the CoNLL 2019 shared task on Cross-Fram... more This paper describes our system (RE-SOLVER) submitted to the CoNLL 2019 shared task on Cross-Framework Meaning Representation Parsing (MRP). Our system implements a transition-based parser with a directed acyclic graph (DAG) to tree preprocessor and a novel cross-framework variable-arity resolve action that generalizes over five different representations. Although we ranked low in the competition, we have shown the current limitations and potentials of including variable-arity action in MRP and concluded with directions for improvements in the future.
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
We introduce a data-driven approach to generating derivation trees from meaning representation gr... more We introduce a data-driven approach to generating derivation trees from meaning representation graphs with probabilistic synchronous hyperedge replacement grammar (PSHRG). SHRG has been used to produce meaning representation graphs from texts and syntax trees, but little is known about its viability on the reverse. In particular, we experiment on Dependency Minimal Recursion Semantics (DMRS) and adapt PSHRG as a formalism that approximates the semantic composition of DMRS graphs and simultaneously recovers the derivations that license the DMRS graphs. Consistent results are obtained as evaluated on a collection of annotated corpora. This work reveals the ability of PSHRG in formalizing a syntaxsemantics interface, modelling compositional graph-to-tree translations, and channelling explainability to surface realization.
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning, 2019
This paper describes our system (RE-SOLVER) submitted to the CoNLL 2019 shared task on Cross-Fram... more This paper describes our system (RE-SOLVER) submitted to the CoNLL 2019 shared task on Cross-Framework Meaning Representation Parsing (MRP). Our system implements a transition-based parser with a directed acyclic graph (DAG) to tree preprocessor and a novel cross-framework variable-arity resolve action that generalizes over five different representations. Although we ranked low in the competition, we have shown the current limitations and potentials of including variable-arity action in MRP and concluded with directions for improvements in the future.