论文信息 - CASIANED: People Attribute Extraction based on Information Extraction

CASIANED: People Attribute Extraction based on Information Extraction

paper, we describe the people attribute extraction system of the CASIANED team for the second Web People search evaluation (WePS-2). We develop an attribute extraction system based on information extraction. Firstly the attribute candidates for every attribute class are extracted using several different information extraction techniques; then these candidates are verified through classification. The system achieves F-measure 0.309 on the develop dataset and F-measure 0.117 on the final test dataset.

Xianpei Han | Jun Zhao

[1] Wei-Ying Ma,et al. Simultaneous record detection and attribute labeling in web data extraction , 2006, KDD '06.

[2] Wai Lam,et al. An unsupervised framework for extracting and normalizing product attributes from multiple web sites , 2008, SIGIR '08.

[3] Bing Liu,et al. Web data extraction based on partial tree alignment , 2005, WWW '05.

[4] Julio Gonzalo,et al. The SemEval-2007 WePS Evaluation: Establishing a benchmark for the Web People Search Task , 2007, Fourth International Workshop on Semantic Evaluations (SemEval-2007).

[5] Rayid Ghani,et al. Text mining for product attribute extraction , 2006, SKDD.

[6] Satoshi Sekine,et al. WePS2 Attribute Extraction Task , 2009 .

[7] Satoshi Sekine,et al. A survey of named entity recognition and classification , 2007 .

[8] Wei-Ying Ma,et al. 2D Conditional Random Fields for Web information extraction , 2005, ICML.

[9] Sujith Ravi,et al. Using structured text for large-scale attribute extraction , 2008, CIKM '08.