An Inference Model for Semantic Entailment in Natural Language
Abstract
Semantic entailment is the problem of determining if the meaning of a given sentence entails that of another. We present a principled approach to semantic entailment that builds on inducing re-representations of text snippets into a hierarchical knowledge representation along with an optimization-based inferential mechanism that makes use of it to prove semantic entailment. This paper provides details and analysis of the knowledge representation and knowledge resources issues encountered. We analyze our system’s behavior on the PASCAL text collection 1 and the PARC collection of question-answer pairs 2. This is used to motivate and explain some of the design decisions in our hierarchical knowledge representation, that is centered around a predicate-argument type abstract representation of text.
Cite
Text
de Salvo Braz et al. "An Inference Model for Semantic Entailment in Natural Language." AAAI Conference on Artificial Intelligence, 2005.Markdown
[de Salvo Braz et al. "An Inference Model for Semantic Entailment in Natural Language." AAAI Conference on Artificial Intelligence, 2005.](https://mlanthology.org/aaai/2005/desalvobraz2005aaai-inference/)BibTeX
@inproceedings{desalvobraz2005aaai-inference,
title = {{An Inference Model for Semantic Entailment in Natural Language}},
author = {de Salvo Braz, Rodrigo and Girju, Roxana and Punyakanok, Vasin and Roth, Dan and Sammons, Mark},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2005},
pages = {1043-1049},
url = {https://mlanthology.org/aaai/2005/desalvobraz2005aaai-inference/}
}