Matching, Re-ranking and Scoring: Learning Textual Similarity by Incorporating Dependency Graph Alignment and Coverage Features

@inproceedings{Kohail2017MatchingRA,
  title={Matching, Re-ranking and Scoring: Learning Textual Similarity by Incorporating Dependency Graph Alignment and Coverage Features},
  author={Sarah Kohail and Chris Biemann},
  year={2017}
}
In this work, we introduce a supervised model for learning textual similarity, which can identify and score similarity between a set of candidate texts and a given query text. By combining dependency graph similarity and coverage features with lexical similarity measures using neural networks, we show that most relevant documents to a given text can be more accurately ranked and scored than if the lexical similarity measures were used in isolation. Additionally, we introduce an approximate… CONTINUE READING
2 Citations
31 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 31 references

Similar Papers

Loading similar papers…