Secteur TAL Informatique,
Université Sorbonne nouvelle, Paris 3

19 rue des Bernardins, 75005 Paris
Secteur TAL Informatique, Université Sorbonne nouvelle, Paris 3

Statistical Natural Language Processing (using Perl)

Vous trouverez ci-dessous, des outils, des textes et des liens "autour" du domaine suivant : "Statistical Natural Language Processing". Ces informations ont été recueillies en particulier à partir du cours développé par J. Goldsmith à l'adresse suivante :

Voir aussi sur la page TP7


Livres de référence

Foundations of Natural Language Processing by Christopher D. Manning and Hinrich Schütze (MIT Press, 1999).

Cours en ligne construits autour de ce livre

UPenn CIS530, UPenn CIS639, Berkeley SIMS 296a-4, Johns Hopkins: current (Eisner) and previous [lots of great slides by Jan Hajic!], Brown CS241, CMU 11-682, CMU 11-761, Stanford CS224N, MIT 6.863, Oregon Graduate Institute CSE580, Ohio State, U Chicago, Tufts, Minnesota, SUNY Albany, San Diego SU, Mississippi State.
U Toronto CSC401, Dalhousie U CSCI4152 [lots of slides!], U Alberta.
Edinburgh Cogsci MSc, Helsinki University of Technology TIK-61.182, Munich, Bochum. Götenborgs
Pohang University of Science and Technology (POSTECH), National Cheng-chi University, Taiwan

Speech and Language Processing by Daniel Jurafsky and James H. Martin (Prentice-Hall, 2000).

Textes disponibles dans cette distribution (PDF)

Textes de J. Goldsmith (PDF ou PowerPoint)


Source for Perl:

Eric Brill's short guide to Perl.



Lectures sur le web

NLP thèmes

Probability and information

Collocations and mutual information.
Use the various Biword frequency Perl scripts I've linked below.

  • basic program for exploring biwords composed of neighboring words.
  • program with more command-line options.

N-gram models over sparse data.

  • Mutual Information : The command line format is much like what you're accustomed to: perl, followed by the name of the data file, the name of the file you wish to output, followed by the parameter p (for "punctuation"). This eliminates punctuation, and it's essential, because if you leave punctuation in, opening the output file with a spreadsheet will confuse the spreadsheet program endlessly (it's the quotations that kill it). The output is a matrix of the top 36 words by frequency, and the frequencies of the biwords constituted of these words. The results are quite striking and interesting! Look at how much blank space there is: this is the sparseness of language. And look at the joint entropy (that's the spread-out-ness of the biwords as a data sample in biword space), and also the mutual information. Notice that the joint entropy plus the mutual information equals the sum of the entropy of the set of words on the left and words on the right.

Inferring morphological structure from a corpus


  • Are there more monosyllables or words of 4 syllables in English? -- in the dictionary, that is. Answer? About 15% of the words in the CMU dictionary are 4-syllables long, and only 13.5% are monosyllables. Run on our (not perfectly syllabified) English word-list (indisponible).
  • What are the most common syllable codas in English? ( Null, n, l, and r, in that order). What is the most common two letter coda? (nt). The most common 3-letter coda? Look it up, or run
  • What are the onsets in English, and how do they compare to word-initial onsets? Run

Statistical Natural Language Processing LINKS


Important statistical tools (system called "R"):

Part of Speech Taggers

Freely downloadable

A fast and flexible implementation of Transformation-Based Learning. Includes a tagger, but also NP chunking, etc.
A Prolog implementation of a Transformation-based Learner (a la Brill), usable for POS tagging and other things by Torbjörn Lager. Web demo also available.
Original Xerox Tagger
A common lisp HMM tagger available by ftp. [Or only used to be?]
Brill's Transformation-based learning Tagger
A C symbolic tagger. Also available by ftp, and as a Windows version, with stuff for French.
A decision tree based tagger from the University of Stuttgart (Helmut Scmid). It's language independent, but comes complete with parameter files for English, German, French, and Italian. (Solaris and Linux versions.) Used at
Maximum Entropy part of speech tagger
By Adwait Ratnaparkhi. JAVA version now downloadable. A sentence boundary detector is also available. [Helpful hint: This only works with JDK1.1. It doesn't work with JDK1.2+.]
QTAG Part of speech tagger
An HMM-based Java POS tagger from Birmingham U. (Oliver Mason).
The TOSCA/LOB tagger.
Currently available for MS-DOS only. But the decision to make this famous system available is very interesting from an historical perspective, and for software sharing in academia more generally. LOB tag set.

Free, but require registration

C taggers by Ingo Schröder that implement maximum entropy, HMM trigram, and transformation-based learning. C source available under GNU public license.
Edinburgh Language Technology Group tagger and text tokenizer (and sentence splitter). Binary only for Solaris. Doesn't allow you to train your own taggers.
TATOO, The ISSCO tagger.
HMM tagger. Need to register to download
PoSTech Korean morphological analyzer and tagger. Follow the links Open Resources - DownLoad.
TnT - A Statistical Part-of-Speech Tagger
Trainable for various languages, comes with English and German pre-compiled models. Runs on Solaris and Linux.

Usable by email or on the web, but not distributed freely

Memory-based tagger
From ILK group, Catholic University Brabant (Jakub Zavrel/Walter Daelemans). Does Dutch, English, Spanish, Swedish, Slovene. Other MBL demos are also available.
Birmingham tagger by email
Accepts only plain ASCII email message contents. The tagset used is similar to the Brown/LOB/Penn set.
CLAWS tagger
The UCREL CLAWS tagger is available for trial use on the web. (It's limited to 300 words though -- this site is more of an advertisement for licensing the real thing -- available as software for Suns or as a paid service.) You can also find info on CLAWS tagsets, though that page doesn't seem to link to the C7 tagset.
The AMALGAM tagger
The AMALGAM Project also has various other useful resources, in particular a web guide to different tag sets in common use. The tagging is actually done by a (retrained) version of the Brill tagger (q.v.).
Xerox XRCE MLTT Part Of Speech Taggers
Tags any of English, Spanish, French, Italian, Portuguese, German, and Dutch, online on the web.
Portuguese tagger (Projecto Natura) on the web

Not free

Lingsoft in Finland has (symbolic) analysis tools for many European languages. More information can be obtained by emailing There is an online demo.
Conexor in Finland has demonstrations of EngCG-style taggers and parsers, for English, Swedish, and Spanish.
Xerox has morphological analyzers and taggers for many languages. There are demos of some of their tools on the web. More information can be obtained by contacting Daniella Russo.


Information on available probabilistic parsers can be found on the FSNLP: probabilistic parsing links page.

Language modeling toolkits


CMU-Cambridge Statistical Language Modeling toolkit

Downloadable, but requires registration

The SRI Language Modeling toolkit
by Andreas Stolcke is another good system for building language models, freely available for research purposes.

Not yet classified

Lextools is a package of tools for creating weighted finite-state transducers (WFST) from high-level linguistic descriptions. Lextools binaries are available free for non-commercial use at: Supported platforms are: linux (i686), sgi (mips2) and sun4. Lextools is built on top of, and requires, the AT&T WFST toolkit (version 3.6), available free for non-commercial use from:

Friendly concordancing and text analysis tools

Wordsmith Tools (Mike Scott)
The thing to get if you are working in the Windows world.



Bigram Statistics Package
Perl code that implements: Fisher's exact test, the likelihood ratio, Pearson's chi squared test, the Dice Coefficient, and Mutual Information.
ISIP tools
The main aim is a publically available speech recognition system (alpha release available), but along the way there are also toolkits for discrete HMMs and statistical decision trees, and for various aspects of signal processing.
Mem. A Perl implementation of Generalized and Improved Iterative Scaling
by Hugo WL ter Doest.
A system (for Windows) for automatically learning the morphological forms of words in a corpus by John Goldsmith.
Wordnet is available by ftp, compiled for a variety of machine types. For money, one can also get EuroWordNet for various European languages.
Penn XTAG project
A wide-coverage tree-adjoining grammar written in a mixture of C and Common Lisp. Also includes a large coverage morphological analyzer. Now includes more tools such as TCL/Tk tree viewer.
Dan Melamed's Tools
A collection of tools including a simulated annealling program, a post-processor for English stemming for the Penn XTAG morphology system, Good-Turing smoothing software, general text processing tools, text statistics tools and bitext geometry tools (mainly written in Perl 5).
Constructing corpora and tools for processing multilingual corpora. Contact: Jean Veronis Some stuff including a multilingual text editor is downloadable.
Naive Bayes algorithm
Software from the Rainbow/Libbow software package that implements several algorithms for text categorization, including naive Bayes, TF.IDF, and probabilistic algorithms. Accompanies Tom Mitchell's ML text.
A prototype Java Summarisation applet (System Quirk)
Emdros: a text database engine for linguistic analysis and research

Free, but require registration

Stuttgart's IMS Corpus Workbench (CWB)
A workbench for full-text retrieval from large corpora (with a query language and corpus indexing). Includes the Corpus Query Processor (CQP) and xkwic. Available free for research groups (currently only as Solaris 1/2 or Linux binaries), on signing a license agreement.
University of Sheffield's General Architecture for Text Engineering. Primarily an Information Extraction system.
MITRE's Alembic Workbench
A workbench for the development of tagged corpora. Includes a tagger based on Brill's TBL approach.
SNoW is a learning program that can be used as a general purpose multi-class classifier and is specifically tailored for learning in the presence of a very large number of features. The learning architecture is a sparse network of linear units over a pre-defined or incrementally acquired feature space (Dan Roth).
Tilburg University's TiMBL
Tilburg's Memory Based Learner. A general near-neighbour-based machine learning package, but optimized for statistical NLP applications. Follow the "Software" link.


a finite-state transducer analysis system for English, French, and Italian that runs under NextStep. Contact: Max Silberztein

The PennTools page collects information on a variety of NLP systems, many of which are available externally.


On-line resources

The best English dictionary resources:

Mike Barlow's corpus linguistics resources:

European language links:

One of many multi-lingual Bible sites: I'm sure there are better; send me one if you find an especially good one.

Many dictionaries from many languages:

Moby Project:

the Penn resources list:

Large collections aimed at the NLP community

LDC (Linguistic Data Consortium)
Email: Provides the largest range of corpora on CD-ROM. Cost ranges from cheap (e.g., ACL-DCI disk) to pricey. CDs can be purchased individually; institutions can become members and receive discounts on CDs. Their catalog and some other info is available by ftp. There's an LDC Online service for searches over the web (mainly intended for members, but there are samplers available).
ACL/DCI (Association for Computational Linguistics Data Collection Initiative)
Email: Results are obtainable through LDC.
European Language Resources Association
Rapidly growing collection of materials in European languages. The RELATOR homepage still exists, which was the first attempt, but its largely moribund, and you should go straight to ELRA.
ICAME (International Computer Archive of Modern English)
Sells various corpora (including Brown and London-Lund). Information on corpora on the web, by sending the message help to, by ftp to Also, manuals for these corpora.
TELRI Research Archive of Computational Tools and Resource. Corpora, many multilingual, in European community languages. Small fee for joining in order to be able to get corpora (unless you have contributed corpora).
CLR (Consortium for Lexical Research)
Email: Focuses more on language processing tools and lexicons, but does have some corpora. As of Feb 1996, you can get most of their stuff by anonymous ftp to Their catalog is available as a postscript file.
OTA (Oxford Text Archive)
Provides mainly literary texts. Has a bright new web site. Email: Most materials are available on the web or by anonymous ftp to Some require negotiations with the providers.
BNC (British National Corpus)
A 100 million word corpus of British English. Now available to people outside the European Union! You can search it online from a simple web interface and there is an index to genres by David Lee and others.
European Corpus Initiative Multilingual Corpus I (ECI/MCI)
A 98 million word corpus, covering most of the major European languages, as well as Turkish, Japanese, Russian, Chinese, and Malay. Cheap. Need to sign a license agreement available at either the WWW site. Also available from the LDC.
Survey of English Usage
At the Department of English Language and Literature at University College London. Includes the British part of ICE, the International Corpus of English project. Now available tag, and parsed for function. 83,419 sentences. Includes ICECUP, dedicated retrieval software. ICE-NZ. ICE-HK. ICE-East Africa is available on the ICAME-2 CD.
Corpora held by Lancaster University
This link provides its own annotations.
The European Language Activity Network
Promises a uniform query language for accessing corpora in all EU languages -- but isn't quite there yet.

Particular languages


English language corpora available from the sites above are not repeated here.

Corpora by Geoffrey Sampson's team
The SUSANNE corpus and the CHRISTINE corpus (SUSANNE markup of a speech corpus).
Penn-Helsinki Parsed Corpus of Middle English
A syntactically annotated corpus of the Middle English prose samples in the Helsinki Corpus of Historical English, with additions. 1.3 million words. $200.
Corpus of Professional, Spoken American-English (CPSA)
2 million words from faculty and committee meetings and White House press conferences (50K work sample free on internet).
Lancaster Parsed Corpus


World Health Organization Computer Assisted Translation page.
Also includes a good selection of links on Computer Assisted Translation. (See also the copyright page.)
Searchable Canadian Hansard French-English parallel texts (1986-1993)
From the Laboratoire de Recherche Appliquée en Linguistique Informatique, Universite de Montréal
European Union web server
Parallel text in all EU languages.
Parallel and other text in central and eastern european languages.


The Oslo Corpus of Bosnian Texts.


Parallel Czech-English
Literature translations in Czech and English
Czech National Corpus project: SYN2000
100 million words of contemporary Czech.
The Prague Dependency Treebank.
Contains half a million words of Czech, analyzed at the levels of parts of speech, syntactic functions (and, in the future, semantic roles) level in a dependency framework. Free on completion of license agreement.
CKIP Chinese Treebank (Taiwan). Based on Academia Sinica corpus.
LDC Chinese Treebank. 100,000 words. More info
LDC Korean Treebank.


Association des Bibliophiles Universels
Various French literary works.
American and French Research on the Treasury of the French Language (ARTFL)
150 million word corpus of various genres of French. You have to be a member to use it (but membership is fairly cheap).


Large online-searchable German corpus
NEGRA Corpus
Saarland University Syntactically Annotated Corpus of German Newspaper Texts. Available free of charge to academics. 20,000 sentences, tagged, and with syntactic structures.


Library of Russian Internet Libraries
Various literary works.


Slovene-English parallel corpus
1 M words, free to download + on-line concordances.
Coming soon: Slovene reference corpus of 100 M words

Spanish and Portuguese

TychoBrahe Parsed Corpus of Historical Portuguese
Over a million words of Portuguese from different historical periods, some of it morphologically analyzed/tagged. Free.
Information about Mark Davies' collection of (mainly historical Spanish and Portuguese.
It's not clear what their availability is.
The CUMBRE corpus. Contact Professor Aquilino Sánchez
The CRATER Spanish corpus
Morphosyntactically tagged telecommunication manuals) is available by ftp.
NLP resources for Portuguese
Lists corpora, dictionaries, terminological databases, tools and other possible pointers of interest.
Folha de S. Paulo newspaper
4 annual CDROMs with full text.
Portuguese-English parallel corpus
See also under ELRA, above.


Spraakdata, Department of Swedish, Göteborgs University.
Has various searcable part of speech tagged Swedish corpora (Parole, Bank of Swedish, etc.), and some material in Zimbabwean languages.


Penn Treebank
Distributed by the LDC.
BLLIP WSJ corpus
Automatically parsed WSJ newswire, distributed by the LDC.
ICE-GB: the British part of ICE, the International Corpus of English project. Tagged and parsed for function. 83,419 sentences.
NEGRA Corpus
Saarland University Syntactically Annotated Corpus of German Newspaper Texts. Available free of charge to academics on completion of license agreement. 20,000 sentences, tagged, and with syntactic structures.
TIGER project. Under construction large collection of parsed German newswire.
Verbmobil Tübingen: under construction treebanked corpus of German, English, and Japanese sentences from Verbmobil (appointment scheduling) data
The Prague Dependency Treebank.
Contains half a million words of Czech, analyzed at the levels of parts of speech, syntactic functions (and, in the future, semantic roles) level in a dependency framework. Free on completion of license agreement.
Syntactic Spanish Database (SDB) University of Santago de Compostela. 160,000 clauses / 1.5 million words.
Bulgarian Treebank. An under construction Bulgarian HPSG treebank. Currently POS-tagged texts are available.
Floresta Sintá(c)tica project: under construction Portuguese treebank.
Dublin-Essex Treebank project
Deriving Linguistic Resources from Treebanks


There are now quite large collections of online literature, available in various languages (though the majority are in English, of course). Below are pointers to some of the main collections:

Entirely or mainly English

Alex: A Catalogue of Electronic Texts on the Internet
Seems to have one of the largest collection. Searching and browsing facilities through gopher menus. Many languages.
Wiretap Electronic Text Archive
Extensive and good quality. Still in the gopher age, though.
The On-line Books Page
The index here only covers books in English, but there are lots of links to other collections of material in all languages.
Project Gutenberg
The oldest and largest project to get out of copyright literature online, freely available. (Or see the mirror, Sailor's Project Gutenberg site.)
The Electronic Text Center of the University of Virginia
Large collection of SGML text, mainly in English, but also in other major languages.
Center for Electronic Texts in the Humanities
Princeton/Rutgers collaboration. They didn't have it together with their web site when I stopped by, but they may soon.
Oxford Electronic Text Library Editions
Available from Oxford University Press, 200 Madison Ave, NY, NY 10016 212-679-7300. The Complete Works of Jane Austen is $95.00, and is reviewed in Computers and the Humanities, 28:4-5 (Aug/Oct, 1994), 317-321.

Acquisition data

CHILDES database.
Database of child language transcriptions in English and many other languages. Texts are also available by ftp. Certain usage requirements. Manuals and programs for accessing the data (the CLAN concordancer) are also available online.


Robin Cover's SGML/XML Web Page
This is a wonderful compendium of information on SGML and XML, including information on the Text Encoding Initiative (TEI). This document is also a guide to many text collections (ones using SGML).
Information about the Text Encoding Initiative (TEI). (The Pizza Chef acts as a TEI tag set selector.)
Microsoft's XML page
W3C XML page.
The Corpus Encoding Standard.
An SGML instance designed for language engineering applications. Also the XML version.


Dictionaries of subcategorization frames

The following dictionaries all list surface subcategorization frames (each with a different annotation scheme). They are also all available in electronic form from the publishers (not free).

Collins Cobuild English Language Dictionary. London: Collins, 1987. The COBUILD web site lets you search their Bank of English corpus (but you need to pay to get more than a trial.
Longman Dictionary of Contemporary English. Burnt Mill, Essex: Longman, 1978.
Oxford Advanced Learner's Dictionary of Current English. Oxford: Oxford University Press, Fourth Edition, 1989. The third edition also had information on subcategorization frames, although in a different incompatible format. However, a partial version of the third edition (with this information) is available free online from the Oxford Text Archive.

Not exactly a dictionary, but another popular source is:

Levin (1993)
Beth Levin. 1993. English Verb Classes and Alternations: A Preliminary Investigation. Chicago. Discusses linguistic distinctions (like unergative/unaccusative verbs, dative shift, etc., not made by the above dictionaries). The index of verbs is online.

See also COMLEX and CELEX available from the LDC.

Dictionaries of assorted languages on the web

The old version of Robert Beard's Web of Online Dictionaries long ago mutated into I'm told the IPO has been delayed. Nevertheless, it's the most comprehensive index of dictionaries available on the web.


U.S. names with frequency information, are available from the Census Bureau.

SGML structured dictionaries

Cambridge International Dictionary of English and other products in SGML.

Lexical/morphological resources

English SENSEVAL Resources
Dictionary entries and tagged examples for 35 words.
ARIES Natural Language Tools
Lexicons and morphological analysis for Spanish. There is a free Prolog demonstrator, but the real lexicons and C/C++ access tools cost money.

Courses, Syllabi, and other Educational Resources


Foundations of Statistical Natural Language Processing
Some information about, and sample chapters from, Christopher Manning and Hinrich Schütze's new textbook, published in June 1999 by MIT Press. Read about courses using this book.
Corpus-based Linguistics
Christopher Manning's Fall 1994 CMU course syllabus (a postscript file).
Statistical NLP: Theory and Practice
Christopher Manning's Spring 1996 CMU course materials.
John Lafferty and Roni Rosenfeld's Spring 1997 CMU course Language and Statistics.
Boston University (John D. Burger and Lynette Hirschman)
A good course and web site, by the looks!
Draft of Data-Intensive Linguistics
By Chris Brew and Marc Moens.
Statistical Natural Language Processing course
By Joakim Nivre. Elsnet suported.
Short Course: Statistical Methods in NLP
By Philip Resnik
Linguist's Guide to Statistics by Brigitte Krenn and Christer Samuelsson.
Statistical and Corpora Based Methods for Processing Natural Languages
By Alon Itai, Technion Computer Science Department. (Don't read those old drafts of mine though ... get the real thing!)
CS 241 Statistical Models in Natural-Language Processing
Eugene Charniak, Brown University.
Michael Littman, Duke: 1997, 1998.

"Corpus Linguistics"

A tutorial on concordances and corpora by Cathy Ball
Web material accompanying McEnery and Wilson's book on Corpus Linguistics
Tony Berber Sardinha's Corpus Linguistics course
Powerpoint slides in an interesting mixture of English and Portuguese (plus the rest of his homepage!)
Concordancing and corpus linguistics
Notes prepared by Phil Benson, Hong Kong University.

Mailing lists

Mailing lists that have information on these topics include:

The main mailing list for info on corpus-based linguistics. Subscribe by sending the message:
subscribe corpora
to Or if you want to subscribe with a different email address, send:
subscribe corpora email-address
(Note that you're now speaking to a Majordomo server, not a listserv, so you don't send your name!). Or you can subscribe on the web.
The empiricist list appears to be defunct now. You used to send a "subscribe" message to

Other stuff on the Web

General resources

Linguistic annotation
A description of formats for linguistic annotation by Steven Bird.
CTI Textual Studies, University of Oxford, Guide to Digital Resources
Lists text analysis tools, corpora, and other stuff.
U. Essex W3-Corpora
Lots of teaching material, links, and online corpora.
Computational Linguistics and NLP (Kenji Kita, Tokushima U.)
A good well organized list of CL references, concentrating on corpus-based and statistical NLP methods. See also Software tools for NLP.
HLT Central
European Human Language Technology site
Survey of the State of the Art in Human Language Technology
ACL SIGLEX list of Lexical Resources
Online materials for a course on Learning Dynamical Systems at Brown University.
Lots of neat info.
Expert Advisory Group for Language Engineering Standards (EAGLES) home page
European standards organization.
Materials prepared for Michael Barlow's Corpus Linguistics course
Corpus Linguistics University of Birmingham
Chris Brew's Teaching Materials for statistical NLP
Not much there last time I looked; you might also try his home page.
Edinburgh LTG HelpDesk's FAQ
Many of the questions in the concern issues related to corpora and tagging.
Content Analysis Resources
Qualitative Text Analysis, Concordances, etc.

Information Retrieval

The SMART IR system
Managing Gigabytes
TREC conference
Text-based Intelligent Systems (Bruce Croft)

Information Extraction/Wrapper Induction

Introduction to Information Extraction Technology. A tutorial by Douglas E. Appelt and David Israel.
Web -> KB. CMU World Wide Knowledge Base project (Tom Mitchell). Has a lot of the best recent probabilistic model IE work, and links to data sets.
RISE: Repository of Online Information Sources Used in Information Extraction Tasks, including links to people, papers, and many widely used data sets, etc. (Ion Muslea)
Message Understanding Conference (MUC) information. A US government funded information extraction exercise (from the 1990s).
Web IR and IE (Einat Amitay). Various links on IR and IE on the web.

People's homepages

Home pages with something useful on them.

University of Texas at Austin Machine Learning Research Group
Steven Abney (until 1997)
Adam Berger
Various stuff on statistical MT and maximum entropy models
Alex Chengyu Fang
Provides a lot of info on the kinds of things they get up to at UCL, without actually giving you anything to play with yourself.


International Quantitative Linguistics Association/Journal of Quantitative Linguistics
Association for Computational Linguistics/Computational Linguistics