The rest of the paper  is organized as follows. Section \ref{sec:desc} describes the dataset and section \ref{sec:fil} defines the task. In section  \ref{sec:lit}, we discuss related literature folowed by a discussion of our method in \ref{sec:mthd}. Following that,  we present the experimental resulsy in \ref{sec:expr}, and discuss and analyze them in \ref{sec:analysis}. Towards the end, we discuss the impact of filtering choices on classification in section \ref{sec:impact}, examine and categorize unfilterable documents in section \ref{sec:unfil}. Finally, we present our conclusions in \ref{}{sec:conc}.

There has been a great deal of interest  as of late on entity-based filtering and ranking.  The Text Analysis Conference   started  Knwoledge Base Population with the goal of developing methods and technologies to fascilitate the creation and population of KBs \cite{ji2011knowledge}. The most relevant track in KBP is entity-linking: given an entity and

a document containing a mention of the entity, identify the mention in the document and link it to the its profile in a KB.  Many studies have attempted to address this task \cite{dalton2013neighborhood, dredze2010entity, davis2012named}. 

 A more recent manifestation of that is the introduction of TREC KBA in 2012.  Following that, there have been a number of research works done on the topic \cite{frank2012building, ceccarelli2013learning, taneva2013gem, wang2013bit, balog2013multi}.  These works are based on KBA 2012 task and dataset  and they address the whole problem of entity filtering and ranking.  TREC KBA continued in 2013, but the task underwent some changes. The main change between  the 2012 and 2013 are in the number of entities, the type of entities, the corpus and the relevance rankings.

}

@inproceedings{ji2011knowledge,

  title={Knowledge base population: Successful approaches and challenges},

  author={Ji, Heng and Grishman, Ralph},

  booktitle={Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1},

  pages={1148--1158},

  year={2011},

  organization={Association for Computational Linguistics}

}

@techreport{singh12:wiki-links,

      author    = {Sameer Singh and Amarnag Subramanya and Fernando Pereira and Andrew McCallum},

      title     = {Wikilinks: A Large-scale Cross-Document Coreference Corpus Labeled via Links to {Wikipedia}},

      institute = {University of Massachusetts, Amherst},

      number    = {UM-CS-2012-015},

      year      = {2012}

}

@inproceedings{dredze2010entity,

  title={Entity disambiguation for knowledge base population},

  author={Dredze, Mark and McNamee, Paul and Rao, Delip and Gerber, Adam and Finin, Tim},

  booktitle={Proceedings of the 23rd International Conference on Computational Linguistics},

  pages={277--285},

  year={2010},

  organization={Association for Computational Linguistics}

}

@inproceedings{dalton2013neighborhood,

  title={A neighborhood relevance model for entity linking},

  author={Dalton, Jeffrey and Dietz, Laura},

  booktitle={Proceedings of the 10th Conference on Open Research Areas in Information Retrieval},

  pages={149--156},

  year={2013},

  organization={LE CENTRE DE HAUTES ETUDES INTERNATIONALES D'INFORMATIQUE DOCUMENTAIRE}

}

@inproceedings{davis2012named,

  title={Named entity disambiguation in streaming data},

  author={Davis, Alexandre and Veloso, Adriano and da Silva, Altigran S and Meira Jr, Wagner and Laender, Alberto HF},

  booktitle={Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers-Volume 1},

  pages={815--824},

  year={2012},

  organization={Association for Computational Linguistics}