Transferring Coreference Resolvers with Posterior Regularization

  title={Transferring Coreference Resolvers with Posterior Regularization},
  author={Andr{\'e} F. T. Martins},
We propose a cross-lingual framework for learning coreference resolvers for resource-poor target languages, given a resolver in a source language. Our method uses word-aligned bitext to project information from the source to the target. To handle task-specific costs, we propose a softmax-margin variant of posterior regularization, and we use it to achieve robustness to projection errors. We show empirically that this strategy outperforms competitive cross-lingual methods, such as delexicalized… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.
11 Citations
53 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 11 extracted citations


Publications referenced by this paper.
Showing 1-10 of 53 references

Summ-it: Um corpus anotado com informações discursivas visando a sumarização automática

  • Sandra Collovini, Thiago Carbonel, Juliana Thiesen Fuchs, Jorge César Coelho, Lúcia Rino, Renata Vieira.
  • Workshop em Tecnologia da Informação e da…
  • 2007
Highly Influential
2 Excerpts

Similar Papers

Loading similar papers…