Elamur Research
☰
home / authors / David McClosky

David McClosky

2 paper cards in the Research library · 2006

David McClosky wrote 2 of the papers Mova reads, in 2006; often with Eugene Charniak, Mark Johnson.

OpenAlex · ORCID · h-index 19 · 9213 citations · 47 works — openalex-snapshot, 2026-10-14

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

Papers

  1. Effective Self-Training for Parsing (2006)
    Self-training of parsers was thought to fail because the parser's own errors are amplified. This paper shows that it works when the self-labelled trees come from a two-stage parser and reranker: the 50-best parses of 24 million unlabelled News sentences are reranked, and the reranker's best tree is added to the Wall…
  2. Reranking and Self-Training for Parser Adaptation (2006)
    Parsers trained on the Wall Street Journal lose much accuracy on other genres: the standard parser scores 89.7% on WSJ but only 82.9% on the Brown corpus.

Co-authors (2)

More papers in the library (1)

Pages of the Research library: our summary, the ideas, references and who cites each.