GENIA Tagger

                   Tsujii laboratory
                  University of Tokyo


1. How to build 

  You need gcc to build the tagger.

  % make

  if you encounter errors with hash, try commenting out "#define USE_HASH_MAP"
  in "maxent.h".


2. How to use

  Prepare a text file containing one sentence per line, then

  % ./geniatagger < TEXTFILE > TAGGEDTEXT

  The tagger outputs the base forms, part-of-speech (POS) tags, chunk tags,
  and named entity (NE) tags in the following tab-separated format.

  word1	base1	POStag1	chunktag1 NEtag1
  word2	base2	POStag2	chunktag2 NEtag2
    :     :        :       :

  Chunks and named entities are represented in the IOB2 format (B for BEGIN,
  I for INSIDE, and O for OUTSIDE). The named entity tagger is trained on
  the NLPBA data set [3], which contains five semantic classes (DNA, RNA,
  cell_line, cell_type, and PROTEIN).


 2.1 Tokenization

  This tagger tokenizes the sentence with almost the same policy as the
  upenn tokenizer (http://www.cis.upenn.edu/~treebank/tokenizer.sed). 

  If you don't want the tagger to perform tokenization, use -nt option.
  In that case, the input sentences should be already tokenized by your
  own tokenizer with white spaces. 


References

[1] Yoshimasa Tsuruoka and Jun'ichi Tsujii, Bidirectional Inference with
    the Easiest-First Strategy for Tagging Sequence Data, Proceedings of
    HLT/EMNLP 2005, pp. 467-474.

[2] Yoshimasa Tsuruoka, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John
    McNaught, Sophia Ananiadou, and Jun'ichi Tsujii, Developing a Robust
    Part-of-Speech Tagger for Biomedical Text, Advances in Informatics -
    10th Panhellenic Conference on Informatics, LNCS 3746, pp. 382-392, 2005

[3] http://research.nii.ac.jp/~collier/workshops/JNLPBA04st.htm

Please send questions and comments to [email protected].
---------------------------------
Tsujii laboratory,
Department of Computer Science,
University of Tokyo
http://www-tsujii.is.s.u-tokyo.ac.jp/