Download | Questions | Mailing Lists | Extensions | Release history | FAQ
Tokenization of raw text is a standard pre-processing step for many NLP tasks. For English, tokenization usually involves punctuation splitting and separation of some affixes like possessives. Other languages require more extensive token pre-processing, which is usually called segmentation.
The Stanford Word Segmenter currently supports Arabic and Chinese. The provided segmentation schemes have been found to work well for a variety of applications.
The system requires Java 1.8+ to be installed. We recommend at least 1G of memory for documents that contain long sentences. For files with shorter sentences (e.g., 20 tokens), decrease the memory requirement by changing the option
java -mx1g in the run scripts.
Arabic is a root-and-template language with abundant bound morphemes. These morphemes include possessives, pronouns, and discourse connectives. Segmenting bound morphemes reduces lexical sparsity and simplifies syntactic analysis.
The Arabic segmenter model processes raw text according to the Penn Arabic Treebank 3 (ATB) standard. It is an implementation of the segmenter described in:
Will Monroe, Spence Green, and Christopher D. Manning. 2014. Word Segmentation of Informal Arabic with Domain Adaptation. In ACL.
Chinese is standardly written without spaces between words (as are some other languages). This software will split Chinese text into a sequence of words, defined according to some word segmentation standard. It is a Java implementation of the CRF-based Chinese Word Segmenter described in:
Huihsin Tseng, Pichuan Chang, Galen Andrew, Daniel Jurafsky and Christopher Manning. 2005. A Conditional Random Field Word Segmenter. In Fourth SIGHAN Workshop on Chinese Language Processing.
Two models with two different segmentation standards are included: Chinese Penn Treebank standard and Peking University standard.
On May 21, 2008, we released a version that makes use of lexicon features. With external lexicon features, the segmenter segments more consistently and also achieves higher F measure when we train and test on the bakeoff data. This version is close to the CRF-Lex segmenter described in:
Pi-Chuan Chang, Michel Galley and Chris Manning. 2008. Optimizing Chinese Word Segmentation for Machine Translation Performance. In WMT.The older version (2006-05-11) without using external lexicon features will still be available for download, but we do recommend using the latest version.
Another new feature of the latest release is that the segmenter can now output k-best segmentations. An example of how to train the segmenter is now also available.
The segmenter is available for download, licensed under the GNU General Public License (v2 or later). Source is included. The package includes components for command-line invocation and a Java API. The segmenter code is dual licensed (in a similar manner to MySQL, etc.). Open source licensing is under the full GPL, which allows many free uses. For distributors of proprietary software, commercial licensing is available. If you don't need a commercial license, but would like to support maintenance of these tools, we welcome gift funding.
The download is a zipped file consisting of model files, compiled code, and source files. If you unpack the tar file, you should have everything needed. Simple scripts are included to invoke the segmenter.
Download Stanford Word Segmenter version 3.5.2
Have a support question? Please ask us on Stack Overflow using the tag stanford-nlp.
Feedback, questions, licensing issues, and bug reports / fixes can also be sent to our mailing lists (see immediately below).
We have 3 mailing lists for
the Stanford Word Segmenter,
all of which are shared
with other JavaNLP tools (with the exclusion of the parser). Each address is
java-nlp-user This is the best list to post to in order
to send feature requests, make announcements, or for discussion among JavaNLP
users. (Please ask support questions on
Stack Overflow using the
You have to subscribe to be able to use this list.
Join the list via this webpage or by emailing
firstname.lastname@example.org. (Leave the
subject and message body empty.) You can also
the list archives.
java-nlp-announce This list will be used only to announce
new versions of Stanford JavaNLP tools. So it will be very low volume (expect 2-4
messages a year). Join the list via this webpage or by emailing
email@example.com. (Leave the
subject and message body empty.)
java-nlp-support This list goes only to the software
maintainers. It's a good address for licensing questions, etc. For
general use and support questions, you're better off using Stack
Overflow or joining and using
You cannot join
java-nlp-support, but you can mail questions to
|3.5.2||2015-04-20||Updated for compatibility|
|3.5.1||2015-01-29||Updated for compatibility|
|3.5.0||2014-10-26||Upgrade to Java 8|
|3.4.1||2014-08-27||Updated for compatibility|
|3.4||2014-06-16||Updated Arabic model|
|3.3.0||2013-11-12||Updated for compatibility|
|3.2.0||2013-06-20||Improved line by line handling|
|1.6.8||2013-04-04||ctb7 model, -nthreads option|
|1.6.7||2012-11-11||Bugfixes for both Arabic and Chinese, Chinese segmenter can now load data from a jar file|
|1.6.6||2012-07-09||Improved Arabic model|
|1.6.5||2012-05-22||Fixed encoding problems, supports stdin for Chinese segmenter|
|1.6.4||2012-05-07||Included Arabic model|
|1.6.3||2012-01-08||Minor bug fixes|
|1.6.2||2011-09-14||Improved thread safety|
|1.6.1||2011-06-19||Fixed empty document bug when training new models||1.6||2011-05-15||Models updated to be slightly more accurate; code correctly released so it now builds; updated for compatibility with other Stanford releases|
|1.5||2008-05-21||(with external lexicon features; able to output k-best segmentations)|
Site design by Bill MacCartney