FRDC's Cross-lingual Entity Linking System at TAC 2013
نویسندگان
چکیده
In this paper, we present FRDC's system at participating in the cross-lingual entity linking (CLEL) tasks for the NIST Text Analysis Conference (TAC) Knowledge Base Population (KBP2013) track. We propose a joint approach for mention expansion, disambiguation, and clustering. In particular, we adopt a lexicon and rule based method for entity classification, a collaborative acronym expansion method and a heuristic combination ranking method that merged ListNet, SVM ranking with web search engine ranking. The results achieved in the TAC cross-lingual entity linking tasks show that our approach is competitive. Our best run achieves 0.655 in B^3+ F1 measure.
منابع مشابه
HITS' Monolingual and Cross-lingual Entity Linking System at TAC 2013
This paper presents HITS’ system for monolingual and cross-lingual entity linking at TAC 2013. The system is an extended version of our last year’s joint entity disambiguation and clustering system based on Markov Logic Networks. We describe the new extensions and discuss the results. The results show that our approach is competitive across all three languages: with a micro-average accuracy of ...
متن کاملTHUNLP at TAC KBP 2013 in Entity Linking
This paper describes the THUNLP system submitted to Entity Linking task of KBP Track in TAC 2013. This system achieves the third place with a B-cubed+ F1 score of 0.712 in mono-lingual entity linking task. In Chinese cross-lingual entity linking, this system achieved B-cubed+ F1 score of 0.647 with the help of Google Translate.
متن کاملHITS' Monolingual and Cross-lingual Entity Linking System at TAC 2012: A Joint Approach
This paper presents HITS’ system for monolingual and cross-lingual entity linking at TAC 2012. We propose a joint system for entity disambiguation, recognition of NILs and clustering using Markov Logic. The proposed model (1) is global, i.e. a group of mentions in a text is disambiguated in one single step combining various global and local features, and (2) performs disambiguation, unknown ent...
متن کاملHITS' Cross-lingual Entity Linking System at TAC 2011: One Model for All Languages
This paper presents HITS’ system for crosslingual entity linking at TAC 2011. We approach the task in three stages: (1) context disambiguation to obtain a language-independent representation, (2) entity disambiguation, (3) clustering of the queries that have not been linked in the second step. For each of these steps one single model is trained and applied to both languages, i.e. English and Ch...
متن کاملECNU: Brief System Description of Submission to Knowledge Base Population at TAC 2011
This paper briefly reports our submissions to the three tasks in TAC KBP 2011, i.e., Slot Filling (SF for short), Entity Linking (EL for short) and Cross-lingual Entity Linking (CEL for short).
متن کامل