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.
Anthology ID:
2022.acl-long.372
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5425–5439
Language:
URL:
https://aclanthology.org/2022.acl-long.372
DOI:
10.18653/v1/2022.acl-long.372
Bibkey:
Cite (ACL):
Chun Hei Lo, Wai Lam, and Hong Cheng. 2022. Semantic Composition with PSHRG for Derivation Tree Reconstruction from Graph-Based Meaning Representations. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5425–5439, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Semantic Composition with PSHRG for Derivation Tree Reconstruction from Graph-Based Meaning Representations (Lo et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.372.pdf