Erik Fäßler | 1 Nov 10:49 2010
Picon
Picon

For students: "CL in Action"

  Hi all,

the new semester has begun and I'm about to plan my first courses. I'd 
like to give the new students some overview about applications of 
Computational Linguistics in the reals world as well as some good 
illustration of the things that happen "behind the scenes" (parsing, 
PoS-Tagging...).
I'm thinking of some slides illustrating standard-techniques like NER, 
parse-tree-generation, for example. Additionally, some actually 
functioning demos would be cool: Perhaps a web-application taking a 
sentence and outputting the parse tree, or the PoS-Tags or whatsoever. 
Or something demonstrating how spelling correction works.
Do you know some resources where some of these things are nicely shown 
and which I could use? Of course I could just do some slides and there 
are plenty of parsers, taggers etc. running in our lab, but it's nothing 
you'd show your fresh students for a first glance ;)

I appreciate any tips!

Thanks,

     Erik

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora

Lionel Nicolas | 1 Nov 10:43 2010
Picon

Re: For students: "CL in Action"

Hello,

Two online parsing/tagging web-applications I'm aware of:
=> for French 
http://alpage.inria.fr/perl/parser.pl
=> for Spanish, English, Italian, Portuguese and others 
http://nlp.lsi.upc.edu/freeling/demo/demo.php

Best,

Lionel  

Le Monday 01 November 2010, Erik Fäßler a écrit :
>   Hi all,
> 
> the new semester has begun and I'm about to plan my first courses. I'd
> like to give the new students some overview about applications of
> Computational Linguistics in the reals world as well as some good
> illustration of the things that happen "behind the scenes" (parsing,
> PoS-Tagging...).
> I'm thinking of some slides illustrating standard-techniques like NER,
> parse-tree-generation, for example. Additionally, some actually
> functioning demos would be cool: Perhaps a web-application taking a
> sentence and outputting the parse tree, or the PoS-Tags or whatsoever.
> Or something demonstrating how spelling correction works.
> Do you know some resources where some of these things are nicely shown
> and which I could use? Of course I could just do some slides and there
> are plenty of parsers, taggers etc. running in our lab, but it's nothing
> you'd show your fresh students for a first glance ;)
> 
(Continue reading)

Erik Fäßler | 1 Nov 10:53 2010
Picon
Picon

Re: For students: "CL in Action"

Hi Adam,

yes, the students are German indeed. This sounds good, I'd really like to take a look. Of course you'd be appropriately credited :)

Can you send me a link where to sign up?

    Erik

Am 01.11.2010 10:45, schrieb Adam Kilgarriff:
Erik,

are the students German?  We've recently produced German word sketches (we have also for various other languages, but they are always MUCH more fun to look at in your mother tongue).  

The application here is lexicography (amongst others, but it's the simplest and most direct): people are using the word sketches to write dictionaries.

They benefit from NLP tools for lemmatisation, POS-tagging and shallow-parsing (as well as others like fast indexing, but that's less NLP-specific).  There are options for viewing the lemmas and POS-tags in the output, and you can click to see tagset documentation.

German word sketches aren't on general release quite yet but I can give you access to a pre-release version if you sign up and give me your username

Adam

On 1 November 2010 09:49, Erik Fäßler <erik.faessler <at> uni-jena.de> wrote:
 Hi all,

the new semester has begun and I'm about to plan my first courses. I'd like to give the new students some overview about applications of Computational Linguistics in the reals world as well as some good illustration of the things that happen "behind the scenes" (parsing, PoS-Tagging...).
I'm thinking of some slides illustrating standard-techniques like NER, parse-tree-generation, for example. Additionally, some actually functioning demos would be cool: Perhaps a web-application taking a sentence and outputting the parse tree, or the PoS-Tags or whatsoever. Or something demonstrating how spelling correction works.
Do you know some resources where some of these things are nicely shown and which I could use? Of course I could just do some slides and there are plenty of parsers, taggers etc. running in our lab, but it's nothing you'd show your fresh students for a first glance ;)

I appreciate any tips!

Thanks,

   Erik

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora



--
================================================
Adam Kilgarriff                                      http://www.kilgarriff.co.uk             
Lexical Computing Ltd                   http://www.sketchengine.co.uk
Lexicography MasterClass Ltd      http://www.lexmasterclass.com
Universities of Leeds and Sussex       adam <at> lexmasterclass.com
================================================

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora
Adam Kilgarriff | 1 Nov 10:45 2010

Re: For students: "CL in Action"

Erik,


are the students German?  We've recently produced German word sketches (we have also for various other languages, but they are always MUCH more fun to look at in your mother tongue).  

The application here is lexicography (amongst others, but it's the simplest and most direct): people are using the word sketches to write dictionaries.

They benefit from NLP tools for lemmatisation, POS-tagging and shallow-parsing (as well as others like fast indexing, but that's less NLP-specific).  There are options for viewing the lemmas and POS-tags in the output, and you can click to see tagset documentation.

German word sketches aren't on general release quite yet but I can give you access to a pre-release version if you sign up and give me your username

Adam

On 1 November 2010 09:49, Erik Fäßler <erik.faessler <at> uni-jena.de> wrote:
 Hi all,

the new semester has begun and I'm about to plan my first courses. I'd like to give the new students some overview about applications of Computational Linguistics in the reals world as well as some good illustration of the things that happen "behind the scenes" (parsing, PoS-Tagging...).
I'm thinking of some slides illustrating standard-techniques like NER, parse-tree-generation, for example. Additionally, some actually functioning demos would be cool: Perhaps a web-application taking a sentence and outputting the parse tree, or the PoS-Tags or whatsoever. Or something demonstrating how spelling correction works.
Do you know some resources where some of these things are nicely shown and which I could use? Of course I could just do some slides and there are plenty of parsers, taggers etc. running in our lab, but it's nothing you'd show your fresh students for a first glance ;)

I appreciate any tips!

Thanks,

   Erik

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora



--
================================================
Adam Kilgarriff                                      http://www.kilgarriff.co.uk             
Lexical Computing Ltd                   http://www.sketchengine.co.uk
Lexicography MasterClass Ltd      http://www.lexmasterclass.com
Universities of Leeds and Sussex       adam <at> lexmasterclass.com
================================================
_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora
Rayson, Paul | 1 Nov 13:06 2010
Picon

Re: For students: "CL in Action"

Hi,

If you want to look at English POS tagging online, see: http://ucrel.lancs.ac.uk/claws/trial.html

For spelling correction in action, the obvious ones would be opening a word processor and mistyping some
text, or you could use the 'correction' feature in Google search.

Paul.

Dr. Paul Rayson
Director of UCREL and Lecturer in Computer Science 
School of Computing and Communications, Infolab21, Lancaster University, Lancaster, LA1 4WA, UK.
Web: http://www.comp.lancs.ac.uk/~paul/
Tel: +44 1524 510357 Fax: +44 1524 510492

-----Original Message-----
From: corpora-bounces <at> uib.no [mailto:corpora-bounces <at> uib.no] On Behalf Of Erik Fäßler
Sent: 01 November 2010 09:49
To: corpora <at> uib.no
Subject: [Corpora-List] For students: "CL in Action"

  Hi all,

the new semester has begun and I'm about to plan my first courses. I'd 
like to give the new students some overview about applications of 
Computational Linguistics in the reals world as well as some good 
illustration of the things that happen "behind the scenes" (parsing, 
PoS-Tagging...).
I'm thinking of some slides illustrating standard-techniques like NER, 
parse-tree-generation, for example. Additionally, some actually 
functioning demos would be cool: Perhaps a web-application taking a 
sentence and outputting the parse tree, or the PoS-Tags or whatsoever. 
Or something demonstrating how spelling correction works.
Do you know some resources where some of these things are nicely shown 
and which I could use? Of course I could just do some slides and there 
are plenty of parsers, taggers etc. running in our lab, but it's nothing 
you'd show your fresh students for a first glance ;)

I appreciate any tips!

Thanks,

     Erik

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora

Angus B. Grieve-Smith | 1 Nov 13:33 2010
Picon

Re: For students: "CL in Action"

On 11/1/2010 5:49 AM, Erik Fäßler wrote:
>  Hi all,
>
> the new semester has begun and I'm about to plan my first courses. I'd 
> like to give the new students some overview about applications of 
> Computational Linguistics in the reals world as well as some good 
> illustration of the things that happen "behind the scenes" (parsing, 
> PoS-Tagging...).
> I'm thinking of some slides illustrating standard-techniques like NER, 
> parse-tree-generation, for example.
     This is only tangentially related to corpora, but can someone 
please explain to me how speech synthesis and recognition got defined 
out of computational linguistics?

--

-- 
				-Angus B. Grieve-Smith
				grvsmth <at> panix.com

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora

Angus B. Grieve-Smith | 1 Nov 15:26 2010
Picon

Re: For students: "CL in Action"

On 11/1/2010 10:06 AM, Yannick Versley wrote:
>>     This is only tangentially related to corpora, but can someone please
>> explain to me how speech synthesis and recognition got defined out of
>> computational linguistics?
> I only have very vague ideas about the "how", but the fact is that speech
> recognition has its own conferences (e.g. InterSpeech, EuroSpeech) and
> that everything related to acoustic models (as opposed to language models)
> doesn't really get the interest of the CL community. I think that fields with a
> strong commercial interest (MT, Speech, IR) tend to split off the main block
> of CL, more readily so when the meat of the typical contribution is in
> technical details
> that can't be wrapped in an easy take-home message for people outside that
> sub-discipline.
     That makes sense, but in universities that have "Introduction to 
Computational Linguistics" classes, there aren't always "Introduction to 
Speech Recognition," or "Introduction to Machine Translation" courses.  
It seems logical then to include those in intro computational 
linguistics courses, but apparently that isn't happening.  Sort of a 
self-reinforcing tribalism here.

--

-- 
				-Angus B. Grieve-Smith
				grvsmth <at> panix.com

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora

amsler | 1 Nov 15:43 2010
Picon

Re: For students: "CL in Action"

Commercial success tends to pull fields out of academic disciplines.  
Whenever the best work is being done by corporations and whenever  
there are commercial products that those corporations are eager to  
keep proprietary, then they tend to focus on keeping their research  
private.

>     That makes sense, but in universities that have "Introduction to
> Computational Linguistics" classes, there aren't always "Introduction
> to Speech Recognition," or "Introduction to Machine Translation"
> courses.  It seems logical then to include those in intro computational
> linguistics courses, but apparently that isn't happening.  Sort of a
> self-reinforcing tribalism here.
>
> -- 
> 				-Angus B. Grieve-Smith
> 				grvsmth <at> panix.com
>
>
> _______________________________________________
> Corpora mailing list
> Corpora <at> uib.no
> http://mailman.uib.no/listinfo/corpora

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora

Mathieu Lafourcade | 1 Nov 21:10 2010
Picon

TALN 2011 - PREMIER APPEL À COMMUNICATIONS

(à diffuser - veuillez-nous excuser des réceptions multiples)

TALN 2011 - PREMIER APPEL À COMMUNICATIONS

TALN 2011
18e Conférence sur le Traitement Automatique des Langues Naturelles
LIRMM/Université Montpellier 2 - CRDP - Du 27 juin au 1er juillet 2011
Site web de la conférence : http://taln2011.org
Date limite de soumission : 22 janvier 2010

PRÉSENTATION

Organisée par le LIRMM (Laboratoire d'Informatique de Robotique et de
Microélectronique) et l'université Montpellier2, la conférence TALN
2011 se tiendra du 27 juin au 1er juillet 2011 à Montpellier. TALN
2011 est organisée sous l'égide de l'ATALA et se tiendra conjointement
avec la conférence pour jeunes chercheurs RECITAL 2011. Elle sera
suivie des ateliers DEFT (DÉfi Fouille de Texte), DEGELS pour (DÉfi,
Geste, Langue des Signes) et DISH (Doctorants, Informatique
et Sciences Humaines).

La conférence TALN 2011 comprendra des communications orales
présentant des travaux de recherche et des prises de position, des
communications affichées, des conférences invitées et des
démonstrations.

La langue officielle de la conférence est le français. Les
communications en anglais sont acceptées pour les participants non
francophones.

TYPES DE COMMUNICATIONS

Deux formats de communications sont prévus : les articles longs (de 8 à 10
pages) et les articles courts (de 4 à 6 pages).
Les auteurs sont invités à présenter deux types de communications :
- Des articles présentant des travaux de recherche originaux
- Des prises de position présentant un point de vue sur l'état des
recherches en TAL (traitement automatique de la langue), fondées sur une
solide expérience du domaine
Les articles longs seront présentés sous forme de communication orale, les
articles courts sous forme de présentation orale ou d'affiche. Il est à
noter que les dates de soumission ont été déterminées de manière à ce qu'un
article long refusé puisse être resoumis comme article court.

CALENDRIER

Articles longs :
- Date limite de soumission : 22 janvier 2010
- Notification aux auteurs : 15 mars 2010
- Version finale : 1er avril 2010
Articles courts :
- Date limite de soumission : 1er avril 2010
- Notification aux auteurs : 15 avril 2010
- Version finale : 1er mai 2010
Conférence : 27 juin - 1er juillet 2010

THÈME

Les communications pourront porter sur tous les thèmes habituels du TAL ou
ceux applicables au TAL, incluant, de manière non limitative :
- Analyse et génération dans les domaines suivants :
  - Phonétique
  - Phonologie
  - Morphologie
  - Syntaxe
  - Sémantique
  - Discours
- Développement de ressources linguistiques pour le TAL :
  - Lexiques
  - Grammaires
  - Bases de données comportant des informations morphologiques,
  syntaxiques, sémantiques, et/ou phonologiques
  - Ontologies
- Applications du TAL :
  - Résumé automatique
  - Dialogue humain-machine en langage naturel
  - Traduction automatique
  - Indexation automatique
  - Recherche et extraction d'information
  - Enseignement assisté par ordinateur
  - Systèmes de question-réponse
  - Résolution d'anaphores
  - Analyse de sentiments ou d'opinions
  - Désambiguïsation lexicale
  - Catégorisation ou classification automatique
  - Web sémantique
- Approches :
  - Linguistiques formelles destinées à soutenir les traitements automatiques
  - Symboliques
  - Logiques
  - Statistiques
  - Basées sur l'apprentissage automatique
Le Comité de programme pourra recommander pour publication en version étendue
au Comité de Rédaction de la revue Traitement Automatique des Langues (t.a.l.)
 le(s) meilleure(s) communication(s) de la conférence.

CRITÈRES DE SÉLECTION

Les soumissions seront examinées par au moins deux spécialistes du domaine.
Seront considérées en particulier pour les articles de recherche :
- L'importance et l'originalité de la contribution
- La correction du contenu scientifique et technique
- La discussion critique des résultats, en particulier par rapport
aux autres travaux du domaine
- La situation des travaux dans le contexte de la recherche internationale
- L'organisation et la clarté de la rédaction
- L'adéquation aux thèmes de la conférence
Pour les prises de position seront privilégiés :
- La largeur de vue et la prise en compte de l'état de l'art
- L'originalité et l'impact du point de vue présenté
Les articles sélectionnés seront publiés dans les actes de la conférence.

FORMAT ET MODALITÉS DE SOUMISSION

Voir les modalités dans la section "Soumission" sur le site de la
conférence (http://taln2011.org)

--

-- 
Mathieu Lafourcade
Maître de Conférence à L'Université Montpellier 2 - LIRMM - Equipe TAL
161, rue ADA  -  F-34392 Montpellier Cedex 5
33 (0)4 67 41 85 71 -- 33 (0)6 09 57 25 91
mathieu.lafourcade <at> lirmm.fr

http://jeuxdemots.org
http://pticlic.org

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora

Yannick Versley | 1 Nov 15:06 2010
Picon

Re: For students: "CL in Action"

>    This is only tangentially related to corpora, but can someone please
> explain to me how speech synthesis and recognition got defined out of
> computational linguistics?
I only have very vague ideas about the "how", but the fact is that speech
recognition has its own conferences (e.g. InterSpeech, EuroSpeech) and
that everything related to acoustic models (as opposed to language models)
doesn't really get the interest of the CL community. I think that fields with a
strong commercial interest (MT, Speech, IR) tend to split off the main block
of CL, more readily so when the meat of the typical contribution is in
technical details
that can't be wrapped in an easy take-home message for people outside that
sub-discipline.

Best,
Yannick

_______________________________________________
Corpora mailing list
Corpora <at> uib.no
http://mailman.uib.no/listinfo/corpora


Gmane