StatFSM 2016

StatFSM 2016: ACL Workshop on statistical NLP and weighted automata

The ACL special interest group on finite-state machines is organizing a one-day workshop on statistical natural language processing and weighted automata co-located with ACL 2016 in Berlin. Topics include but are not limited to:

  • weighted automata, their theory and applications,
  • statistical NLP; in particular approaches using finite-state techniques,
  • the formal relation between statistical models and weighted automata,
  • automata-based implementations or approximations of statistical methods,
  • machine learning of finite-state models of natural language.

Special Theme: Automata-based techniques in optical character recognition

Optical character recognition (OCR) has become an important research area in natural language processing. We meet this development with a special theme on automata-based techniques in OCR, including topics such as:

  • systems and frameworks for OCR or optical layout recognition (OLR), particularly those with a connection to automata-based methods,
  • statistical approaches to automated document analysis,
  • supervised or unsupervised extraction of lexica, language- or error-models for OCR post-correction,
  • systems and frameworks for post-correction or segmentation of OCR output texts, especially those making use of finite-state automata.