Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Core Semantic First: A Top-down Approach for AMR Parsing

About

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.

Deng Cai, Wai Lam• 2019

Related benchmarks

TaskDatasetResultRank
AMR parsingLDC2017T10 AMR 2.0 (test)
Smatch73.2
168
AMR Similarity ConsistencyBAMBOO (test)
Main - STS-B53.06
17
AMR parsingLDC2017T10 (test)
Smatch (ordinary)73.2
6
Showing 3 of 3 rows

Other info

Code

Follow for update