We welcome original research papers that identify key problems related to noisy text analytics and offer solutions. Potential topics include (but not limited to):

  • Information Retrieval and Information Extraction on noisy texts
  • IR-related tasks (classification, clustering, genre recogntion, document summarization, QA, keyword search, ...) on noisy texts
  • Formal models for noise, characterization and classification of noise
  • Linguistic analysis of noisy textual data (robust parsing, OOV handling,...)
  • Treatment of noisy data in special application fields
    • Historical Texts
    • Multilingual Texts 
    • Blogs
    • Chat logs/SMS 
    • Social Network Analysis
    • Business Intelligence
    • Patent Search
    • Optical Character Recognition
    • Automated Speech Recognition
    • Machine Translation 
  • Data sets, benchmarks and evaluation techniques for analysis of noisy texts

Selected papers from the workshop will be included in a special issue of the International Journal of Document Analysis and Recognition published by Springer. 

 

We are pleased to note that selected papers from the first AND workshop -- held in January 2007 at the IJCAI conference in Hyderabad, India -- appeared in a special issue of the International Journal of Document Analysis and Recognition published by Springer less than a year after the workshop date. For the table of contents, follow this link.


Download AND 08 CFP in pdf