Transition-Based Dependency Parsing with Heuristic Backtracking

  title={Transition-Based Dependency Parsing with Heuristic Backtracking},
  author={Jacob Buckman and Miguel Ballesteros and Chris Dyer},
We introduce a novel approach to the decoding problem in transition-based parsing: heuristic backtracking. This algorithm uses a series of partial parses on the sentence to locate the best candidate parse, using confidence estimates of transition decisions as a heuristic to guide the starting points of the search. This allows us to achieve a parse accuracy comparable to beam search, despite using fewer transitions. When used to augment a Stack-LSTM transition-based parser, the parser shows an… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 15 references

Beam Search with Dynamic Pruning for Artificial Intelligence Hard Problems

2013 International Conference on Mechatronics, Electronics and Automotive Engineering • 2013
View 2 Excerpts

Similar Papers

Loading similar papers…