Empirical Inference
Article
2009
Inferring textual entailment with a probabilistically sound calculus
PDF Web
Empirical Inference
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. |
| Links: | |
| Journal: | Natural Language Engineering |
| Volume: | 15 |
| Number (issue): | 4 |
| Pages: | 459-477 |
| Year: | 2009 |
| Month: | October |
| Day: | 0 |
| BibTeX Type: | Article (article) |
| DOI: | 10.1017/S1351324909990118 |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
BibTeX
@article{6081,
title = {Inferring textual entailment with a probabilistically sound calculus},
journal = {Natural Language Engineering},
abstract = {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.},
volume = {15},
number = {4},
pages = {459-477},
organization = {Max-Planck-Gesellschaft},
school = {Biologische Kybernetik},
month = oct,
year = {2009},
author = {Harmeling, S.},
doi = {10.1017/S1351324909990118},
month_numeric = {10}
}