English

SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance

Computation and Language 2023-06-02 v2

Abstract

The similarity of graph structures, such as Meaning Representations (MRs), is often assessed via structural matching algorithms, such as Smatch (Cai and Knight, 2013). However, Smatch involves a combinatorial problem that suffers from NP-completeness, making large-scale applications, e.g., graph clustering or search, infeasible. To alleviate this issue, we learn SMARAGD: Semantic Match for Accurate and Rapid Approximate Graph Distance. We show the potential of neural networks to approximate Smatch scores, i) in linear time using a machine translation framework to predict alignments, or ii) in constant time using a Siamese CNN to directly predict Smatch scores. We show that the approximation error can be substantially reduced through data augmentation and graph anonymization.

Keywords

Cite

@article{arxiv.2203.13226,
  title  = {SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance},
  author = {Juri Opitz and Philipp Meier and Anette Frank},
  journal= {arXiv preprint arXiv:2203.13226},
  year   = {2023}
}

Comments

to appear at 15th International Conference on Computational Semantics (IWCS 2023)

R2 v1 2026-06-24T10:24:59.170Z