@article{doan2009information,
  abstract = {Over the past few years, we have been trying to build an end-to-end system at Wisconsin to manage unstructured data, using extraction, integration, and user interaction. This paper describes the key information extraction (IE) challenges that we have run into, and sketches our solutions. We discuss in particular developing a declarative IE language, optimizing for this language, generating IE provenance, incorporating user feedback into the IE process, developing a novel wiki-based user interface for feedback, best-effort IE, pushing IE into RDBMSs, and more. Our work suggests that IE in managing unstructured data can open up many interesting research challenges, and that these challenges can greatly benefit from the wealth of work on managing structured data that has been carried out by the database community.},
  acmid = {1519106},
  address = {New York, NY, USA},
  author = {Doan, AnHai and Naughton, Jeffrey F. and Ramakrishnan, Raghu and Baid, Akanksha and Chai, Xiaoyong and Chen, Fei and Chen, Ting and Chu, Eric and DeRose, Pedro and Gao, Byron and Gokhale, Chaitanya and Huang, Jiansheng and Shen, Warren and Vuong, Ba-Quy},
  doi = {10.1145/1519103.1519106},
  interhash = {b80d6ce47b976503692def4e86b0097d},
  intrahash = {fccc9f25a1c70cb71d3377a7ddfe1614},
  issn = {0163-5808},
  issue_date = {December 2008},
  journal = {SIGMOD Record},
  month = mar,
  number = 4,
  numpages = {7},
  pages = {14--20},
  publisher = {ACM},
  title = {Information extraction challenges in managing unstructured data},
  url = {http://doi.acm.org/10.1145/1519103.1519106},
  volume = 37,
  year = 2009
}