01whole.pdf (3.63 MB)
Download file

Methods for taking semantic graphs apart and putting them back together again

Download (3.63 MB)
posted on 29.03.2022, 01:19 authored by Jonas Groschwitz
This thesis develops the AM dependency parser, a semantic parser for Abstract Meaning Representation (AMR, Banarescu et al. (2013)) that owes its strong performance to its effective combination of neural and compositional methods. Neural networks have proven to be enormously effective machine learning tools for natural language processing. Compositionality as a linguistic principle it has a strong tradition in semantic construction. However, both approaches have distinct challenges. Pure neural models are data hungry, since they have no prior knowledge of the inherent structure in language. Compositional approaches have robustness issues and suffer from the ambiguity of latent structural information in the training data. This thesis combines the strengths of both worlds to address these challenges. The AM dependency parser drops the restrictive syntactic constraints of classic compositional approaches, instead relying only on semantic types and meaningful semantic operations as structural guides. The ability of neural networks to encode contextual information allows the parser to make correct decisions in the absence of hard syntactic constraints. Consequently, the thesis focuses on terms for semantic representations, which are algebraic `building instructions'. The thesis frst examines the suitability of the HR algebra (a general tool for building graphs, Courcelle and Engelfriet (2012)) for this purpose. It then develops the linguistically motivated AM algebra, that proves much better suited for the purpose. Representing the terms over the AM algebra as dependency trees further simplifies the semantic construction. In particular, the move from the HR algebra to the AM algebra and then to AM dependency trees drastically removes the ambiguity of latent structural information required for training the model. In conclusion, the AM dependency trees yield a simple semantic parser, where neural tagging and dependency models predict interpretable, meaningful operations that construct the AMR.


Table of Contents

1. Introduction -- 2. Background : semantic graphs, and building them piece by piece -- 3. Background : semantic parsing -- 4. S-graph decompisotion -- 5. The AM algebra -- 6. AM dependency parsing -- 7. Conclusion -- Bibliography -- Appendices.


Bibliography: pages 223-230 Empirical thesis. "PhD thesis developed at the Philosophische Fakultät, Saarland university and the Department of Computing at Macquarie University" -- title page.

Awarding Institution

Macquarie University

Degree Type

Thesis PhD


PhD, Macquarie University, Faculty of Science and Engineering, Department of Computing

Department, Centre or School

Department of Computing

Year of Award


Principal Supervisor

Mark Johnson

Additional Supervisor 1

Alexander Koller


Copyright Jonas Groschwitz 2019. Copyright disclaimer: http://mq.edu.au/library/copyright






1 online resource (xviii, 244 pages) diagrams, graphs, tables

Former Identifiers

mq:71045 http://hdl.handle.net/1959.14/1270278