We present a general learning-based approach for phrase-level sentiment analysis that adopts an ordinal sentiment scale and is explicitly compositional in nature. Thus, we can mod...
—Recognition of document images having Greek polytonic (multi accent) characters is a challenging task due the large number of existing character classes (more than 270). In this...
We presented a novel procedure to extract ground road networks from airborne LiDAR data. First point clouds were separated into ground and non-ground parts, and ground roads were ...
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
We propose the first joint model for word segmentation, POS tagging, and dependency parsing for Chinese. Based on an extension of the incremental joint model for POS tagging and ...
Jun Hatori, Takuya Matsuzaki, Yusuke Miyao, Jun-ic...