NiCT at TREC 2010: Related Entity Finding
نویسندگان
چکیده
This paper describes experiments carried out at NiCT for the TREC 2010 Entity track. Our studies mainly focus on improving the NE Extraction and Ranking Entity modules, both of them play vital roles in Related Entity Finding system. In our last year’s system, only a Named Entity Recognition tool is used to extract entities that match coarse-grained types of target entities such as organization, person, etc. In this year, dependency tree-based patterns learnt automatically are employed to filter out entities that do not match fine-grained types of target entities such as university, airline, author, etc. In the Entity Ranking part, we propose a dependency tree-based similarity method and incorporate homepage information to improve ranking.
منابع مشابه
NiCT at TREC 2009: Employing Three Models for Entity Ranking Track
This paper describes experiments carried out at NiCT for the TREC 2009 Entity Ranking track. Our main study is to develop an effective approach to rank entities via measuring the “similarities” between supporting snippets of entities and input query. Three models are implemented to this end. 1) The DLM regards entity ranking as a task of calculating the probabilities of generating input query g...
متن کاملA Multiple-Stage Framework for Related Entity Finding: FDWIM at TREC 2010 Entity Track
This paper describes a multiple-stage retrieval framework for the task of related entity finding on TREC 2010 Entity Track. In the document retrieval stage, search engine is used to improve the retrieval accuracy. In the entity extraction and filtering stage, we extract entity with NER tools, Wikipedia and text pattern recognition. Then stoplist and other rules are employed to filter entity. De...
متن کاملLADS: Rapid Development of a Learning-To-Rank Based Related Entity Finding System using Open Advancement
In this paper, we present our system called LADS, tailored to work on the TREC Entity Track Task of Related Entity Finding. The LADS system consists of four key components: document retrieval, entity extraction, feature extraction and entity ranking. We adopt the open advancement framework for the rapid development and use a learning-to-rank approach to rank candidate entities. We also experime...
متن کاملPRIS at TREC 2010: Related Entity Finding Task of Entity Track
This paper reports the approaches to the task of Entity Track applied by PRIS lab of BUPT in TREC 2010. We used Document-Centered Model (DCM) and Entity-Centered Model (ECM) for the task. BM25 method was introduced into ECM besides indri retrieval model. Another improvement aimed at entity extraction. Special web page, NER tool and entity list generated by some rules were all taken into account...
متن کامل