Parsing Publication Lists on the Web

Researchers usually present their publication records (we call citation records in this paper) on publication lists on the Web, which could be an important data source for many applications to collect more publication records than from some digital libraries, such as DBLP. However, it is still not easy to design an algorithm to extract citation records from publication lists because of the diversity of page layouts and citation formats. In this paper, we propose an automatic approach to extract citation records from publication list pages by utilizing two properties. First, citation records are usually represented as nodes at the same level in the DOM tree. Second, citation records in the same page are presented by similar HTML tags. Extensive experiments are conducted to measure the effects of all parameters and system performance. Experiment results show that our approach performs stable and well (with 86.2% of F-measure on average).