Tools Installed at OSU and their Reference Documentation

This list of resources was collected by Markus Dickinson and Detmar Meurers (OSU), February 2002. Funding for this project provided by OSU College of Humanities Seed Grant.

• Tokenization/Segmentation Tools
• Taggers
• Morphological Analyzers
• Parsers/Chunkers
• Various Tools (Annotate, Search and Transcribe)

Go to the corpus resources page or view the locally installed corpora.

TOKENIZATION / SEGMENTATION

• LT TTT (Text Tokenisation Tool)

  found at: /opt/compling/src/TTT_v1.0/

  • The TTT Manual (html one-page, html multipage)

• SATZ

  found at: /opt/compling/src/satz-1.0/ (README)

• MXTERMINATOR

  found at: /opt/compling/src/Ratnaparkhi/

  • Instructions: html

TAGGERS

• Decision Tree Tagger

  found at: /opt/compling/lib/tree-tagger/ (README)

• Xerox Tagger

  found at: /opt/compling/src/XeroxTagger/

  • User's Guide: ps

• TnT

  found at: /opt/compling/src/tnt/

  • Manual: pdf, ps

• Brill Taggers

  • Supervised

    found at: /opt/compling/src/Tagger/RULE_BASED_TAGGER_V1.14/ (README.FIRST, README.QUICK, README.LONG, README.NBEST, README.TRAINING)

  • Unsupervised

    found at: /opt/compling/src/Tagger/Unsup-Learn/ (README)

• MXPOST

  found at: /opt/compling/src/Ratnaparkhi/

  • Instructions: html

• MuTBL

  found at: /opt/compling/src/Mutbl/

  • The User's Manual: html
  • The Programmer's Manual: html

• SNoW-based Tagger

  found at: /opt/compling/src/roth-tagger (README.POS)

  • The Snow User's Guide: ps

MORPHOLOGICAL ANALYZERS

• Morphix

  found at: /opt/compling/src/morphix/

  • A description: html
  • New features: txt

• morpha and morphg

  found at: /opt/compling/src/english-morph/ (README)

• PC-KIMMO

  found at: /opt/compling/pckimmo/

  • Version 1 Manual: man
  • Version 2 (The manual in 7 files):
    1. Intro: txt, pdf
    2. Overview: txt, pdf
    3. Englex: txt, pdf
    4. Reference Manual: txt, pdf
    5. Rules Component: txt, pdf
    6. Two-level phonology: txt, pdf
    7. References: txt, pdf

PARSERS

• Link Grammar Parser

  found at: /opt/compling/src/link-grammar-system-4.1/(README)

• SNoW-based Shallow Parser

  found at: /opt/compling/src/shallow-parser (README)

  • The Snow User's Guide: ps

• Collins Parser

  found at: /opt/compling/src/Collins/parser (README, README.models)

• nlparser (Charniak)

  found at: /opt/compling/src/charniak (README)

• LoPar

  found at: /opt/compling/src/LoPar-2.8

  • System description: ps

VARIOUS TOOLS (ANNOTATE, SEARCH, TRANSCRIBE)

• TIGERSearch

  found at: /opt/compling/TIGERSearch

  • The TIGERSearch Manual (pdf, ps.gz)
  • The TIGERRegistry Manual (pdf, ps.gz)
  • The TIGERXML Manual (pdf, ps.gz)

  To represent trees, TIGERSearch uses Scalable Vector Graphics (SVG), which are viewed using Batik at: /opt/batik-1.1.1/docs/index.html

• CQP (Corpus Query Processor) and Xkwic

  found at: /opt/compling/ims-cwb/cwb-3.0

  • The User's Manual (ps)
  • A tutorial for CQP (pdf, ps)
  • The Technical Manual (ps)
  • The Xkwic Manual (ps)

• The CLaRK System

  found at: /home/compling/src/ClarkSystem/

  • Manual: pdf, ps

• AGTK (Annotation Graph ToolKit)

  found at: /opt/compling/src/agtk/

  • AGTK Application Developer's Manual: pdf, ps
  • LDC MultiTrans transcription tool User Manual: html, txt
  • LDC TableTrans annotation tool User Manual (currently unavailable)

• tgrep

  found at: /home/corpora/EN/penn_treebank_2/tools/ (README.T)

  To use, set TGREP_CORPUS variable to /home/corpora/EN/penn_treebank_2/tgrepabl/wsj_mrg.crp

Questions or comments? Contact Markus Dickinson.