Joint Learning for Coreference Resolution with Markov Logic

  title={Joint Learning for Coreference Resolution with Markov Logic},
  author={Yang Song and Jing Jiang and Wayne Xin Zhao and Sujian Li and Houfeng Wang},
Pairwise coreference resolution models must merge pairwise coreference decisions to generate final outputs. Traditional merging methods adopt different strategies such as the bestfirst method and enforcing the transitivity constraint, but most of these methods are used independently of the pairwise learning methods as an isolated inference procedure at the end. We propose a joint learning model which combines pairwise classification and mention clustering with Markov logic. Experimental results… CONTINUE READING
Highly Cited
This paper has 23 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 14 extracted citations


Publications referenced by this paper.
Showing 1-10 of 30 references

Similar Papers

Loading similar papers…