[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Bug#605919: ITP: mbt -- memory-based tagger-generator and tagger for natural language processing



Package: wnpp
Severity: wishlist
Owner: Joost van Baal <joostvb-debian-bugs-20101204-3@mdcc.cx>

* Package name    : mbt
  Version         : 3.2.2
  Upstream Author : ILK Research Group, Tilburg University, http://ilk.uvt.nl
* URL             : http://ilk.uvt.nl/mbt
* License         : GPL-3
  Programming Lang: C++
  Description     : memory-based tagger-generator and tagger for natural language processing

 MBT is a memory-based tagger-generator and tagger in one. The tagger-generator
 part can generate a sequence tagger on the basis of a training set of tagged
 sequences; the tagger part can tag new sequences. MBT can, for instance, be
 used to generate part-of-speech taggers or chunkers for natural language
 processing.  Features:
  * Tagger generation: tagged text in, tagger out,
  * Optional feedback loop: feed previous tag decision back to input of next
    decision,
  * Easily customizable feature representation; can incorporate user-provided
    features,
  * Automatic generation of separate sub-taggers for known words and unknown
    words,
  * Can make use of full algorithmic parameters of TiMBL.
 .
 If you do scientific research in natural language processing, MBT will
 likely be of use to you.

---

MBT depends upon TiMBL, see Bug#605913: ITP: timbl -- Tilburg Memory Based
Learner.

The current MBT upstream release is available from
http://ilk.uvt.nl/downloads/pub/software/mbt-3.2.2.tar.gz .  Debian packages
are available from

 deb http://apt.ticc.uvt.nl lenny main
 deb-src http://apt.ticc.uvt.nl lenny main

. You can find e.g.
http://apt.ticc.uvt.nl/pool/main/m/mbt/mbt_3.2.2-1.dsc there.

See also Bug#605905: ITP: frog -- tagger and parser for Dutch language .

Bye,

Joost

Attachment: signature.asc
Description: Digital signature


Reply to: