Alireza Mohammadshahi
Alireza Mohammadshahi wrote 2 of the papers Mova reads, in 2020–2021, most of them on Dependency parsing, Treebanks; often with James Henderson.
Topics: Dependency parsing 2 · Treebanks 1
Papers
- Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement (2021)
The parser predicts all edges of a graph in parallel, then refines the whole graph in recursive passes. Each pass is conditioned on the graph from the previous pass. An initial parser supplies the first graph, and the paper refines both UDify output and its own graph parser (SynTr). Refinement reduces LAS error… - Graph-to-Graph Transformer for Transition-based Dependency Parsing (2020)
The paper proposes the Graph2Graph Transformer (G2GTr), an architecture that conditions on an arbitrary graph and predicts one.
Co-authors (1)
This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/alireza-mohammadshahi/