Ryan McDonald

6 paper cards in Mova's library · 2005–2016

Ryan McDonald wrote 6 of the papers Mova reads, in 2005–2016, most of them on Dependency parsing, Universal Dependencies, Treebanks; often with Fernando Pereira, Joakim Nivre, Jan Hajič.

OpenAlex · h-index 48 · 16372 citations · 113 works — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Dependency parsing 5 · Universal Dependencies 1 · Treebanks 1 · Part-of-speech tagging 1

Ideas Mova took (2)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

kept — Error profile by distance to the root in en parse-eval and in gparse (Eisner decoding, gparse/src/eisner.rs): precision and recall of arcs at distance 1, 2, 3–4 and 5 or more, on EWT test; the question is whether the arc-standard parser fragments the tree… (Characterizing the Errors of Data-Driven Dependency Parsing… · en parse-diag, EWT dev our tags: labelled recall by depth 1/2/3-4/5+ = 87.16/77.33/79.62/78.76 (depth 2 weakest); by arc length 1..7+ 86.8 -> 56.8; commit…)
kept — Non-projectivity split: report LAS separately for sentences with a gold arc of degree 1 or more; the arc-standard parser in en/src/parse.rs cannot build those arcs, so the number is its ceiling on EWT and GUM test (GUM is test only). (Characterizing the Errors of Data-Driven Dependency Parsing… · en parse-diag: 33 of 2001 dev sentences non-projective (39 arcs, 0.16%), LAS 72.57 vs 79.67; non-projectivity costs at most 0.16 LAS; commit 3ba5388e8)

Papers

Universal Dependencies v1: A Multilingual Treebank Collection (2016)
The paper is the reference for the first UD release. It sets out the design principles: dependency-based and lexicalist annotation, the recoverability principle (every syntactic word must map back to the raw text), content words as the backbone of the tree with function words as dependents, and a closed inventory of…
Evaluation of Dependency Parsers on Unbounded Dependencies (2010)
Unbounded dependencies, such as an object that is extracted from a relative clause, are a standard test of grammar-based parsers, but had not been applied to dependency parsers.
Characterizing the Errors of Data-Driven Dependency Parsing Models (2007) 2 ideas kept
The paper compares the two top systems of the CoNLL-X shared task. MSTParser is a global, exhaustive graph-based model with maximum spanning tree decoding and arc-pair features; MaltParser is a local, greedy transition-based model with an SVM classifier. Both reach almost the same labeled accuracy over 13 languages…
Online Learning of Approximate Dependency Parsing Algorithms (2006)
The maximum spanning tree framework scores a tree as a sum of arc scores, which cannot see neighbouring decisions.
Online Large-Margin Training of Dependency Parsers (2005)
The paper trains a linear, edge-scored dependency parser with online MIRA, a margin-based update that changes the weights as little as possible while the correct tree beats the k best wrong trees by a loss-dependent margin.
Non-Projective Dependency Parsing using Spanning Tree Algorithms (2005)
The paper casts weighted dependency parsing as a search for maximum spanning trees in a directed graph. Eisner's algorithm covers all projective trees in O(n^3), and the Chu-Liu-Edmonds algorithm covers non-projective trees in O(n^2), with the same edge scores. The scores are trained with online large-margin learning…

Co-authors (16)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/ryan-mcdonald/