The NLPRIR Entity Linking System at TAC 2012
نویسندگان
چکیده
In this paper, we describe our KBP Entity Lining system at TAC 2012. Our system consists of three modules. 1) Query expansion and candidate entity selection module. In this module, we identify all the possible entities for an entity mention through a variety knowledge sources. 2) Entity disambiguation module. In this module, we use a maximum margin approach to rank the candidate entity. 3) NIL clustering module. In this module, we cluster all the NIL entities which have been detected in the second module using Hierarchical Agglomerative Clustering alrorithm.
منابع مشابه
Context-Based Entity Linking - University of Amsterdam at TAC 2012
This paper describes our approach to the 2012 Text Analysis Conference (TAC) Knowledge Base Population (KBP) entity linking track. For this task, we turn to a state-of-the-art system for entity linking in microblog posts. Compared to the little context microblog posts provide, the documents in the TAC KBP track provide context of greater length and of a less noisy nature. In this paper, we adap...
متن کاملMSR System for Entity Linking at TAC 2012
The paper describes the system submitted to TAC 2012 for the English entity linking task of the Knowledge Base Population track. It focuses on the components that are novel with reference to the MSR system that participated in TAC 2011. Three runs were submitted for evaluation, and the best of them achieved the highest B-cubed+ F score of all systems participating in this evaluation (0.730) and...
متن کاملLIA at TAC KBP 2012 English Entity Linking track
This paper describes our participation in the English Entity Linking task at KBP 2012.
متن کاملBasis Technology at TAC 2013 Entity Linking
Basis Technology participated in the TAC Entity-Link task of the Knowledge Base Population track at TAC 2013. This paper describes the system we developed and runs submitted for English, Chinese, and Spanish evaluation. The system is an extended and improved version of the system used in TAC 2012. We focus on the novel components and error analysis.
متن کاملJVN-TDT Entity Linking Systems at TAC-KBP2012
We present two methods for entity linking in two of our systems submitted to TAC-KBP 2012. The first one, implemented in JVNTDT1 system, learns coherence among cooccurrence entities referred to within a text by exploiting Wikipedia’s link structure and the second one, implemented in JVN_TDT2 system, combines some heuristics with a statistical model, for entity linking. The method implemented in...
متن کامل