Sense-level Subjectivity in a Multilingual Setting
Carmen Banea, Rada F. Mihalcea, Janyce Wiebe · 2011
This paper explores the ability of senses aligned across languages to carry coherent subjectivity information. We start out with a manual annotation study, and then seek to create an automatic framework to determine subjectivity labeling for unseen senses. We identify two methods that are able to incorporate subjectivity information originating from different languages, namely co-training and multilingual vector spaces, and show that for this task the latter method is better suited and obtains superior results.