English

Learning to Transpile AMR into SPARQL

Computation and Language 2022-12-12 v2

Abstract

We propose a transition-based system to transpile Abstract Meaning Representation (AMR) into SPARQL for Knowledge Base Question Answering (KBQA). This allows us to delegate part of the semantic representation to a strongly pre-trained semantic parser, while learning transpiling with small amount of paired data. We depart from recent work relating AMR and SPARQL constructs, but rather than applying a set of rules, we teach a BART model to selectively use these relations. Further, we avoid explicitly encoding AMR but rather encode the parser state in the attention mechanism of BART, following recent semantic parsing works. The resulting model is simple, provides supporting text for its decisions, and outperforms recent approaches in KBQA across two knowledge bases: DBPedia (LC-QuAD 1.0, QALD-9) and Wikidata (WebQSP, SWQ-WD).

Keywords

Cite

@article{arxiv.2112.07877,
  title  = {Learning to Transpile AMR into SPARQL},
  author = {Mihaela Bornea and Ramon Fernandez Astudillo and Tahira Naseem and Nandana Mihindukulasooriya and Ibrahim Abdelaziz and Pavan Kapanipathi and Radu Florian and Salim Roukos},
  journal= {arXiv preprint arXiv:2112.07877},
  year   = {2022}
}
R2 v1 2026-06-24T08:17:50.403Z