Now showing items 1-4 of 4
Deep Understanding of a Document's Structure
Current language understanding approaches focus on small documents, such as newswire articles, blog posts, product reviews and discussion forum discussions. Understanding and extracting information from large documents ...
A Unified Bayesian Model of Scripts, Frames and Language
(AAAI Press, 2016-02-12)
We present the first probabilistic model to capture all levels of the Minsky Frame structure, with the goal of corpus-based induction of scenario definitions. Our model unifies prior efforts in discourse-level modeling ...
Unsupervised techniques for discovering ontology elements from Wikipedia article links
(Association for Computational Linguistics, 2010-06-06)
We present an unsupervised and unrestricted approach to discovering an infobox like ontology by exploiting the inter-article links within Wikipedia. It discovers new slots and fillers that may not be available in the ...
Improving Binary Classification on Text Problems using Differential Word Features
We describe an efficient technique to weigh word-based features in binary classification tasks and show that it significantly improves classification accuracy on a range of problems. The most common text classification ...