Semantic Composition with PSHRG for Derivation Tree Reconstruction from Graph-Based Meaning Representations
Chun Hei Lo, Wai Lam, Hong Cheng
Abstract
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 syntax–semantics interface, modelling compositional graph-to-tree translations, and channelling explainability to surface realization.
BibTeX
@inproceedings{lo-etal-2022-semantic,
title = "Semantic Composition with {PSHRG} for Derivation Tree Reconstruction from Graph-Based Meaning Representations",
author = "Lo, Chun Hei and
Lam, Wai and
Cheng, Hong",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.372/",
doi = "10.18653/v1/2022.acl-long.372",
pages = "5425--5439"
}