Core Semantic First: A Top-down Approach for AMR Parsing
This work addresses AMR parsing for natural language processing, offering a novel top-down approach that improves performance in extracting core semantic structures, though it is incremental in method.
The authors tackled AMR parsing by introducing Graph Spanning based Parsing (GSP), a top-down method that incrementally builds parse graphs from the root, and achieved state-of-the-art performance on the latest AMR sembank without heuristic graph re-categorization, with the parser excelling at capturing core semantics.
We introduce a novel scheme for parsing a piece of text into its Abstract Meaning Representation (AMR): Graph Spanning based Parsing (GSP). One novel characteristic of GSP is that it constructs a parse graph incrementally in a top-down fashion. Starting from the root, at each step, a new node and its connections to existing nodes will be jointly predicted. The output graph spans the nodes by the distance to the root, following the intuition of first grasping the main ideas then digging into more details. The \textit{core semantic first} principle emphasizes capturing the main ideas of a sentence, which is of great interest. We evaluate our model on the latest AMR sembank and achieve the state-of-the-art performance in the sense that no heuristic graph re-categorization is adopted. More importantly, the experiments show that our parser is especially good at obtaining the core semantics.