Naïve but effective NIL clustering baselines - CMCRC at TAC 2011
نویسندگان
چکیده
This paper describes the CMCRC systems entered in the TAC 2011 entity linking challenge. We used our best-performing system from TAC 2010 to link queries, then clustered NIL links. We focused on naı̈ve baselines that group by attributes of the top entity candidate. All three systems performed strongly at 75.4% B F1, above the 71.6% median score.
منابع مشابه
SYDNEY CMCRC at TAC 2013
We use a supervised whole-document approach to English Entity Linking with simple clustering approaches. The system extends our TAC 2012 system (Radford et al., 2012), introducing new features for modelling local entity description and type-specific matching as well type-specific supervised models and supervised NIL classification. Our rule-based clustering takes advantage of local description ...
متن کامل(Almost) Total Recall - SYDNEY CMCRC at TAC 2012
We explore unsupervised and supervised whole-document approaches to English NEL with naı̈ve and context clustering. Our best system uses unsupervised entity linking and naı̈ve clustering and scores 66.5% B+ F1 score. Our KB clustering score is competitive with the top systems at 65.6%.
متن کاملSaarland University Spoken Language Systems Group at TAC KBP 2011
In this paper we describe our participation in the Knowledge Base Population (KBP) track at TAC 2011. The architecture of our slot filling system is the same as last year. We mainly focus on developing a new system for the cross-language entity linking task. We compare the performance of monolingual retrieval and cross-lingual retrieval for entity linking. For NIL entity clustering, we group re...
متن کاملDocument-level Entity Linking: CMCRC at TAC 2010
This paper describes the CMCRC systems entered in the TAC 2010 entity linking challenge. The best performing system we describe implements the document-level entity linking system from Cucerzan (2007), with several additions that exploit global information. Our implementation of Cucerzan’s method achieved a score of 74.9% in development experiments. Additional global information improves perfor...
متن کاملThe CASIA Entity linking System at TAC 2013
In this paper, we describe our entity linking system at TAC-KBP 2013. Our system consists of four modules. 1) Query expansion module. 2) Candidate generation module. 3) Candidate Entity disambiguation module. 4) NIL clustering module. First, we expand the queries with the information of the query documents. Then we find the candidates of queries from the Knowledge Base using the WikiPedia knowl...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011