A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing

@inproceedings{Dai2019ARA,
  title={A Regularization Approach for Incorporating Event Knowledge and Coreference Relations into Neural Discourse Parsing},
  author={Zeyu Dai and Ruihong Huang},
  booktitle={EMNLP/IJCNLP},
  year={2019}
}
We argue that external commonsense knowledge and linguistic constraints need to be incorporated into neural network models for mitigating data sparsity issues and further improving the performance of discourse parsing. Realizing that external knowledge and linguistic constraints may not always apply in understanding a particular context, we propose a regularization approach that tightly integrates these constraints with contexts for deriving word representations. Meanwhile, it balances… CONTINUE READING

Figures, Tables, and Topics from this paper.

Explore Further: Topics Discussed in This Paper

References

Publications referenced by this paper.
SHOWING 1-10 OF 62 REFERENCES

Deep Contextualized Word Representations

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

The Penn Discourse Treebank

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Bidirectional recurrent neural networks

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL