We derive two variants of a semi-supervised model for fine-grained sentiment analysis. Both models leverage abundant natural supervision in the form of review ratings, as well as...
Word space models, in the sense of vector space models built on distributional data taken from texts, are used to model semantic relations between words. We argue that the high dim...
Mining bilingual data (including bilingual sentences and terms1 ) from the Web can benefit many NLP applications, such as machine translation and cross language information retrie...
Long Jiang, Shiquan Yang, Ming Zhou, Xiaohua Liu, ...
In this paper, we propose a method for 3D-model retrieval from one or more photos. This method provides an ”optimal” selection of 2D views to represent a 3D-model, and a proba...
Whole-book recognition is a document image analysis strategy that operates on the complete set of a book’s page images, attempting to improve accuracy by automatic unsupervised ...