@misc{gleave2017a,
   title = {Making compression algorithms for {U}nicode text},
   author = {Adam Gleave and Christian Steinruecken},
   year = {2017},
   month = jan,
   eprint = {arXiv:1701.04047 [cs.IT]},
   howpublished = {{\tt arXiv:1701.04047 [cs.IT]}},
   note = {\url{http://arxiv.org/abs/1701.04047}},
   abstract = {
      The majority of online content is written in languages other 
      than English, and is most commonly encoded in UTF-8, the 
      world's dominant Unicode character encoding. Traditional 
      compression algorithms typically operate on individual bytes. 
      While this approach works well for the single-byte ASCII 
      encoding, it works poorly for UTF-8, where characters often 
      span multiple bytes. Previous research has focused on 
      developing Unicode compressors from scratch, which often failed 
      to outperform established algorithms such as bzip2.  We develop 
      a technique to modify byte-based compressors to operate 
      directly on Unicode characters, and implement variants of LZW 
      and PPM that apply this technique. We find that our method 
      substantially improves compression effectiveness on a UTF-8 
      corpus, with our PPM variant outperforming the state-of-the-art 
      PPMII compressor. On ASCII and binary files, our variants 
      perform similarly to the original unmodified compressors.
   },
}