The Second Open Knowledge Extraction Challenge

The Open Knowledge Extraction (OKE) challenge, at its second edition, has the ambition to provide a reference framework for research on Knowledge Extraction from text for the Semantic Web by re-defining a number of tasks (typically from information and knowledge extraction), taking into account specific SW requirements. The OKE challenge defines two tasks: (1) Entity Recognition, Linking and Typing for Knowledge Base population; (2) Class Induction and entity typing for Vocabulary and Knowledge Base enrichment. Task 1 consists of identifying Entities in a sentence and create an OWL individual representing it, link to a reference KB (DBpedia) when possible and assigning a type to such individual. Task 2 consists in producing rdf:type statements, given definition texts. The participants will be given a dataset of sentences, each defining an entity (known a priori). The following systems participated to the challenge: WestLab to both Task 1 and 2, ADEL and Mannheim to Task 2 only. In this paper we describe the OKE challenge, the tasks, the datasets used for training and evaluating the systems, the evaluation method, and obtained results.

[1]  Jens Lehmann,et al.  Integrating NLP Using Linked Data , 2013, SEMWEB.

[2]  Nicola Guarino,et al.  Sweetening Ontologies with DOLCE , 2002, EKAW.

[3]  Tim Berners-Lee,et al.  Linked Data - The Story So Far , 2009, Int. J. Semantic Web Inf. Syst..

[4]  Erik F. Tjong Kim Sang,et al.  Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition , 2002, CoNLL.

[5]  Jens Lehmann,et al.  DBpedia - A crystallization point for the Web of Data , 2009, J. Web Semant..

[6]  Mark A. Przybocki,et al.  The Automatic Content Extraction (ACE) Program – Tasks, Data, and Evaluation , 2004, LREC.

[7]  Amal Zouaq,et al.  Entity Typing and Linking Using SPARQL Patterns and DBpedia , 2016, SemWebEval@ESWC.

[8]  Georgios Paliouras,et al.  Ontology Population and Enrichment: State of the Art , 2011, Knowledge-Driven Multimedia Information Extraction and Ontology Evolution.

[9]  Raphaël Troncy,et al.  Enhancing Entity Linking by Combining NER Models , 2016, SemWebEval@ESWC.

[10]  Stefano Faralli,et al.  DWS at the 2016 Open Knowledge Extraction Challenge: A Hearst-Like Pattern-Based Approach to Hypernym Extraction and Class Induction , 2016, SemWebEval@ESWC.

[11]  Ralph Grishman,et al.  Message Understanding Conference- 6: A Brief History , 1996, COLING.

[12]  Amal Zouaq,et al.  Collective Disambiguation and Semantic Annotation for Entity Linking and Typing , 2016, SemWebEval@ESWC.

[13]  Erik F. Tjong Kim Sang,et al.  Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition , 2003, CoNLL.

[14]  Raphaël Troncy,et al.  GERBIL: General Entity Annotator Benchmarking Framework , 2015, WWW.

[15]  Axel-Cyrille Ngonga Ngomo,et al.  CETUS - A Baseline Approach to Type Extraction , 2015, SemWebEval@ESWC.

[16]  Andrea Giovanni Nuzzolese,et al.  Open Knowledge Extraction Challenge , 2015, SemWebEval@ESWC.