We present a novel learning framework for pipeline models aimed at improving the communication between consecutive stages in a pipeline. Our method exploits the confidence scores ...
We propose a novel HMM-based framework to accurately transliterate unseen named entities. The framework leverages features in letteralignment and letter n-gram pairs learned from ...
Bing Zhao, Nguyen Bach, Ian R. Lane, Stephan Vogel
In this paper, we describe some experiments in large-scale Information Extraction (IE) focusing on book texts. We investigate the scalability of IE techniques to full-sized books,...
Several NLP tasks are characterized by asymmetric data where one class label NONE, signifying the absence of any structure (named entity, coreference, relation, etc.) dominates al...
At present, adapting an Information Extraction system to new topics is an expensive and slow process, requiring some knowledge engineering for each new topic. We propose a new par...