Adaptive Parameters for Entity Recognition with Perceptron HMMs

  title={Adaptive Parameters for Entity Recognition with Perceptron HMMs},
  author={Massimiliano Ciaramita and Olivier Chapelle},
We discuss the problem of model adaptation for the task of named entity recognition with respect to the variation of label distributions in data from different domains. We investigate an adaptive extension of the sequence perceptron, where the adaptive component includes parameters estimated from unlabelled data in combination with background knowledge in the form of gazetteers. We apply this idea empirically on adaptation experiments involving two newswire datasets from different domains and… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Explore Further: Topics Discussed in This Paper


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

Similar Papers

Loading similar papers…