TongKey at Entity Track TREC 2011: Related Entity Finding
Zhengcai Pan, Haiguang Chen · 2011
This paper presents our work done for the TREC 2011 Entity track. A retrieval model was proposed for the task of related entity finding. This model consists of several parts: In order to get more accurate document collection, query analysis method was utilized to format the narrative of each query. Then, our dataset was generated by using ClueWeb09 API 2 . Moreover, we employed the NER tools and text pattern recognition to extract entities from this processed dataset. In particular, the types of target entities are not so well-defined as last year. Therefore, a specific classifier trained by employing Wikipedia titles and category was utilized to identify the categories of target entities. To find related entity homepages and supporting documents, a set of feature-based methods were applied.