When is Self-Training Effective for Parsing?

  title={When is Self-Training Effective for Parsing?},
  author={David McClosky and Eugene Charniak and Mark Johnson},
Self-training has been shown capable of improving on state-of-the-art parser performance (McClosky et al., 2006) despite the conventional wisdom on the matter and several studies to the contrary (Charniak, 1997; Steedman et al., 2003). However, it has remained unclear when and why selftraining is helpful. In this paper, we test four hypotheses (namely, presence of a phase transition, impact of search errors, value of non-generative reranker features, and effects of unknown words). From these… CONTINUE READING
Highly Cited
This paper has 56 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.

56 Citations

Citations per Year
Semantic Scholar estimates that this publication has 56 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 14 references

Coarseto-fine n-best parsing and MaxEnt discriminative reranking

  • Charniak, Eugene, Mark Johnson.
  • InProc. of the 2005 Meeting of the Assoc. for…
  • 2005

A syntaxbased statistical translation model

  • Yamada, Kenji, Kevin Knight.
  • In
  • 2001

Similar Papers

Loading similar papers…