2010 · 37 citations · 37 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningNatural Language ProcessingInformation ExtractionKnowledge AcquisitionKnowledge ExtractionParsingQuestion AnsweringSelf-supervised LearningDomain Knowledge AcquisitionHierarchical StructuresMachine Reading ComprehensionQuestion Answering Systems
Machine reading is a long-standing goal of AI and NLP. In recent years, tremendous progress has been made in developing machine learning approaches for many of its subtasks such as parsing, information extraction, and question answering. However, existing end-to-end solutions typically require substantial amount of human efforts (e.g., labeled data and/or manual engineering), and are not well poised for Web-scale knowledge acquisition. In this paper, we propose a unifying approach for machine reading by bootstrapping from the easiest extractable knowledge and conquering the long tail via a self-supervised learning process. This self-supervision is powered by joint inference based on Markov logic, and is made scalable by leveraging hierarchical structures and coarse-to-fine inference. Researchers at the University of Washington have taken the first steps in this direction. Our existing work explores the wide spectrum of this vision and shows its promise. 1
37
Extracting product features and opinions from reviews
Ana-Maria Popescu, Oren Etzioni · 2005 · 1.7K citations · Full text
Open information extraction from the web
Michele Banko, Michael Cafarella, Stephen Soderland et al. · 2007 · 1.3K citations
Unsupervised named-entity extraction from the Web: An experimental study
Oren Etzioni, Michael Cafarella, Doug Downey et al. · Artificial Intelligence · 2005 · 1.1K citations
Wrapper induction for information extraction
Nicholas Kushmerick, Daniel S. Weld · 1997 · 1K citations