Findings from University of British Columbia Provide New Insights into Natural Language Engineering

摘要

2011 AUG 1 - (VerticalNews.com) -- "In this work we investigate four subjectivityrnand polarity tasks on spoken and written conversations. We implement and compare severalrnpattern-based subjectivity detection approaches, including a novel technique wherein subjectivernpatterns are learned from both labeled and unlabeled data, using n-gram word sequences withrnvarying levels of lexical instantiation," investigators in Vancouver, Canada report.