To search or to crawl?: towards a query optimizer for text-centric tasks
Proceedings of the 2006 ACM SIGMOD international conference on Management of data
Yago: a core of semantic knowledge
Proceedings of the 16th international conference on World Wide Web
Freebase: a collaboratively created graph database for structuring human knowledge
Proceedings of the 2008 ACM SIGMOD international conference on Management of data
Open information extraction from the web
Communications of the ACM - Surviving the data deluge
Database and information-retrieval methods for knowledge discovery
Communications of the ACM - A Direct Path to Dependable Software
Proceedings of the twenty-eighth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Open information extraction from the web
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Data integration for the relational web
Proceedings of the VLDB Endowment
Acquisition of instance attributes via labeled and related instances
Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval
Scalable knowledge harvesting with high precision and high recall
Proceedings of the fourth ACM international conference on Web search and data mining
Structured relation discovery using generative models
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Identifying relations for open information extraction
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Hi-index | 0.00 |
Dynamic content is a frequently accessed part of the Web. However, most information extraction approaches are batch-oriented, thus not effective for gathering rapidly changing data. This paper proposes a model for fact extraction in real-time. Our model addresses the difficult challenges that timely fact extraction on frequently updated data entails. We point out a naive solution to the main research question and justify the choices we make in the model we propose.