Inferring textual entailment with a probabilistically sound calculus
2009
Article
ei
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): | Empirische Inferenz |
Bibtex Type: | Article (article) |
Digital: | 0 |
DOI: | 10.1017/S1351324909990118 |
Language: | en |
Organization: | Max-Planck-Gesellschaft |
School: | Biologische Kybernetik |
Links: |
PDF
Web |
BibTex @article{6081, 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}, doi = {10.1017/S1351324909990118}, month_numeric = {10} } |