Corpus ID: 12141896

When logical inference helps determining textual entailment ( and when it doesn ’ t )

@inproceedings{BosWhenLI,
  title={When logical inference helps determining textual entailment ( and when it doesn ’ t )},
  author={Johan Bos and K. Markert}
}

Johan Bos, K. Markert

We compare and combine two methods to approach the second textual entailment challenge (RTE-2): a shallow method based mainly on word-overlap and a method based on logical inference, using first-order theorem proving and model building techniques. We use a machine learning technique to combine features of both methods. We submitted two runs, one using only the shallow features, yielding an accuracy of 61.6%, and one using features of both methods, performing with an accuracy score of 60.6… CONTINUE READING

let.rug.nl

Save to Library

Create Alert

Cite

Launch Research Feed