AMR Dependency Parsing with a Typed Semantic Algebra
Saarland University（萨尔兰大学）；Macquarie University（麦考瑞大学）
英文摘要：
We present a semantic parser for Abstract Meaning Representations which learns to parse strings into tree representations of the compositional structure of an AMR graph. This allows us to use standard neural techniques for supertagging and dependency tree parsing, constrained by a linguistically principled type system. We present two approximative decoding algorithms, which achieve state-of-the-art accuracy and outperform strong baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
