Radiopharmaceutical Chemistry in Peking University (PKU)

Peking University at DUC 2006

This paper has described a summary extraction system implemented by Peking University at DUC 2006. The system follows the assumption that there must exist some sentences which can summarize the topic briefly. Then our system depends on various features to judge whether a sentence is appropriately included in the summary. Our results are satisfying in the evaluations including linguistic quality...

Chinese Word Segmentation at Peking University

Word segmentation is the first step in Chinese information processing, and the performance of the segmenter, therefore, has a direct and great influence on the processing steps that follow. Different segmenters will give different results when handling issues like word boundary. And we will present in this paper that there is no need for an absolute definition of word boundary for all segmenter...

Radiochemistry and Radiopharmaceutical Chemistry for Medicine

Shades of grey: radiopharmaceutical chemistry in the 1990s and beyond.

Science, like the universe itself, is ever expanding. The fields of biochemistry, physiology and pharmacology are rapidly growing, and radiopharmaceutical chemistry is no exception. In a recent Editorial Dr William C. Eckelman briefly reviewed the current status of radiopharmaceutical development (Eckelman, 1991). The ballots are out and returns are mixed. Radiopharmaceutical chemists have made...

Peking University at TRECVID 2008: High Level Feature Extraction

We participated in one task of TRECVID 2008, that is, the high-level feature extraction (HLFE). This paper presents our approaches and results on the HLFE task. We mainly focus on exploring the data imbalance learning in this year, and propose two methods for this problem: (1) adaptive borderline-SMOTE and under-sampling SVM (ABUSVM), and (2) concept category. Our approach can be divided into t...