Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents

@inproceedings{Zhang2016DependencySC,
  title={Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents},
  author={Rui Zhang and Honglak Lee and Dragomir R. Radev},
  booktitle={HLT-NAACL},
  year={2016}
}
The goal of sentence and document modeling is to accurately represent the meaning of sentences and documents for various Natural Language Processing tasks. In this work, we present Dependency Sensitive Convolutional Neural Networks (DSCNN) as a generalpurpose classification system for both sentences and documents. DSCNN hierarchically builds textual representations by processing pretrained word embeddings via Long ShortTerm Memory networks and subsequently extracting features with convolution… CONTINUE READING
Highly Cited
This paper has 39 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 10 times over the past 90 days. VIEW TWEETS
29 Citations
35 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 29 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 35 references

Similar Papers

Loading similar papers…