%0 Conference Paper %1 Gerber2011 %A Gerber, Daniel %A Ngonga Ngomo, Axel-Cyrille %B 1st Workshop on Web Scale Knowledge Extraction @ ISWC 2011 %D 2011 %K 2011 SIMBA boa event_iswc event_wekex gerber group_aksw ngonga %T Bootstrapping the Linked Data Web %X Most knowledge sources on the Data Web were extracted from structured or semi-structured data. Thus, they encompass solely a small fraction of the information available on the document-oriented Web. In this paper, we present BOA, an iterative bootstrapping strategy for extracting RDF from unstructured data. The idea behind BOA is to use the Data Web as background knowledge for the extraction of natural language patterns that represent predicates found on the Data Web. These patterns are used to extract instance knowledge from natural language text. This knowledge is finally fed back into the Data Web, therewith closing the loop. We evaluate our approach on two data sets using DBpedia as background knowledge. Our results show that we can extract several thousand new facts in one iteration with very high accuracy. Moreover, we provide the first repository of natural language representations of predicates found on the Data Web.

@inproceedings{Gerber2011, abstract = {Most knowledge sources on the Data Web were extracted from structured or semi-structured data. Thus, they encompass solely a small fraction of the information available on the document-oriented Web. In this paper, we present BOA, an iterative bootstrapping strategy for extracting RDF from unstructured data. The idea behind BOA is to use the Data Web as background knowledge for the extraction of natural language patterns that represent predicates found on the Data Web. These patterns are used to extract instance knowledge from natural language text. This knowledge is finally fed back into the Data Web, therewith closing the loop. We evaluate our approach on two data sets using DBpedia as background knowledge. Our results show that we can extract several thousand new facts in one iteration with very high accuracy. Moreover, we provide the first repository of natural language representations of predicates found on the Data Web.}, added-at = {2024-03-04T14:14:09.000+0100}, author = {Gerber, Daniel and {Ngonga Ngomo}, Axel-Cyrille}, biburl = {https://www.bibsonomy.org/bibtex/28225ebcc3c8f29f053b7684d47dd66c7/aksw}, booktitle = {1st Workshop on Web Scale Knowledge Extraction @ ISWC 2011}, interhash = {0918df367910dce80d220f6ac428fd59}, intrahash = {8225ebcc3c8f29f053b7684d47dd66c7}, keywords = {2011 SIMBA boa event_iswc event_wekex gerber group_aksw ngonga}, owner = {gerb}, timestamp = {2024-03-04T14:14:09.000+0100}, title = {Bootstrapping the Linked Data Web}, year = 2011 }