@InProceedings{petri-cohn:2016:COLINGTuto,
  author    = {Petri, Matthias  and  Cohn, Trevor},
  title     = {Succinct Data Structures for NLP-at-Scale},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Tutorial Abstracts},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {20--21},
  abstract  = {Succinct data structures involve the use of novel data structures,
	compression technologies, and other mechanisms to allow data to be
	stored in extremely small memory or disk footprints, while still
	allowing for efficient access to the underlying data. They have
	successfully been applied in areas such as Information Retrieval and
	Bioinformatics to create highly compressible in-memory search indexes 
	which provide efficient search functionality over datasets
	which traditionally could only be processed using external memory
	data structures. 
	Modern technologies in this space are not well known
	within the NLP community, but have the potential to revolutionise NLP,
	particularly the application to `big data' in the form of terabyte and
	larger corpora. This tutorial will present a practical introduction to
	the most important succinct data structures, tools, and applications
	with the intent of providing the researchers with a jump-start into
	this domain. The focus of this tutorial will be efficient text processing 
	utilising space efficient representations of suffix arrays,
	suffix trees and searchable integer compression schemes with
	specific applications of succinct data structures to
	common NLP tasks such as $n$-gram language modelling.
	Author{1}{Affiliation}},
  url       = {http://aclweb.org/anthology/C16-3006}
}