Header logo is ei

Inferring textual entailment with a probabilistically sound calculus




We introduce a system for textual entailment that is based on a probabilistic model of entailment. The model is defined using a calculus of transformations on dependency trees, which is characterized by the fact that derivations in that calculus preserve the truth only with a certain probability. The calculus is successfully evaluated on the datasets of the PASCAL Challenge on Recognizing Textual Entailment.

Author(s): Harmeling, S.
Journal: Natural Language Engineering
Volume: 15
Number (issue): 4
Pages: 459-477
Year: 2009
Month: October
Day: 0

Department(s): Empirical Inference
Bibtex Type: Article (article)

Digital: 0
DOI: 10.1017/S1351324909990118
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF


  title = {Inferring textual entailment with a probabilistically sound calculus},
  author = {Harmeling, S.},
  journal = {Natural Language Engineering},
  volume = {15},
  number = {4},
  pages = {459-477},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = oct,
  year = {2009},
  month_numeric = {10}