Learning to Prune: Context-Sensitive Pruning for Syntactic MT

  title={Learning to Prune: Context-Sensitive Pruning for Syntactic MT},
  author={Wenduan Xu and Yue Zhang and Philip Williams and Philipp Koehn},
We present a context-sensitive chart pruning method for cky-style MT decoding. Source phrases that are unlikely to have aligned target constituents are identi ed using sequence labellers learned from the parallel corpus, and speed-up is obtained by pruning corresponding chart cells. The proposed method is easy to implement, orthogonal to cube pruning and additive to its pruning power. On a full-scale English-to-German experiment with a string-to-tree model, we obtain a speed-up of more than 60… CONTINUE READING

From This Paper

Topics from this paper.
1 Citations
18 References
Similar Papers


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 18 references

Rimell: Chart pruning for fast lexicalisedgrammar parsing

  • Y. Zhang, B. G. Ahn, S. Clark, C. Van Wyk J.R. Curran
  • In Proc. COLING,
  • 2010
1 Excerpt

Efficient parsing for transducer grammars

  • M. Hopkins, K. Knight, D. Marcu
  • Proc . NAACL - HLT
  • 2009

Curran: The importance of su- pertagging for wide-coverage ccg parsing

  • J.R.S. Clark
  • In Proc. COLING,
  • 2004

The importance of su - pertagging for wide - coverage ccg parsing

  • Michael Collins
  • Proc . COLING
  • 2004

Similar Papers

Loading similar papers…