Fernando Pereira

4 paper cards in Mova's library · 2005–2007

Fernando Pereira wrote 4 of the papers Mova reads, in 2005–2007, most of them on Dependency parsing, Treebanks; often with Ryan McDonald, Jan Hajič, João Graça.

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

Papers

Frustratingly Hard Domain Adaptation for Dependency Parsing (2007)
The authors report their entry to the 2007 CoNLL shared task on domain adaptation, where parsers had to adapt to new domains without labelled target data.
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…