[Corpora-List] dependency-based semantic role labeling annotation tool (Mikhail Kozhevnikov)

Sarwat Nizamani saniz at mmmi.sdu.dk
Wed Apr 25 19:25:40 CEST 2012


Hi Mikhail, I have also the same problem the source code runs error free, but what I want is to give plain text sentence as input to the srl, and get the predicate argument structure of the sentence as the output is given in the online demo of the same system. Thanks

Best Regards,

Sarwat Nizamani Maersk McKinney Moller Institute, University of Southern, Denmark. ________________________________________ From: corpora-bounces at uib.no [corpora-bounces at uib.no] On Behalf Of corpora-request at uib.no [corpora-request at uib.no] Sent: Wednesday, April 25, 2012 10:02 AM To: corpora at uib.no Subject: Corpora Digest, Vol 58, Issue 30

Today's Topics:

1. dependency-based semantic role labeling annotation tool

(Mohammad Sadegh Rasooli)

2. Re: dependency-based semantic role labeling annotation tool

(Mikhail Kozhevnikov)

3. Re: dependency-based semantic role labeling annotation tool

(Mohammad Sadegh Rasooli)

4. Request (Asif Anjum)

5. Re: dependency-based semantic role labeling annotation tool

(Mikhail Kozhevnikov)

6. Re: Request (Laurence Anthony)

7. New International MSc Intelligent Adaptive Systems

(Stefan Wermter)

8. WG: Job opening: professorship at Universität des

Saarlandes, Saarbrücken (Germany) (Kerstin Kunz)

9. Re: dependency-based semantic role labeling annotation tool

(anders bjorkelund)

10. Re: Request (Serge Heiden)

11. Re: Request (maxwell)

12. *SEM 2012 Registration is now open (Eneko Agirre)

13. age-of-acquisition norms for over 50 thousand English words

(Marc Brysbaert)

14. Call for Papers: SocInfo 2012 (Lausanne, Switzerland)

(Cristian Danescu-Niculescu-Mizil)

15. Call for Papers: Workshop on Practice and Theory of Opinion

Mining and Sentiment Analysis (Vienna, Austria) (Michael Wiegand)

16. Re: Request (fatima zuhra)

17. Re: dependency-based semantic role labeling annotation tool

(Mohammad Sadegh Rasooli)

18. Re: dependency-based semantic role labeling annotation tool

(Emad Mohamed)

----------------------------------------------------------------------

Message: 1 Date: Tue, 24 Apr 2012 15:23:27 +0430 From: Mohammad Sadegh Rasooli <rasooli.ms at gmail.com> Subject: [Corpora-List] dependency-based semantic role labeling

annotation tool To: corpora <corpora at uib.no>

Dear corpora users,

Is there any available dependency-based semantic role labeling annotation tool?

Thanks -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 146 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120424/02a59f92/attachment.txt>

------------------------------

Message: 2 Date: Tue, 24 Apr 2012 13:07:04 +0200 From: Mikhail Kozhevnikov <amblerr at gmail.com> Subject: Re: [Corpora-List] dependency-based semantic role labeling

annotation tool To: Mohammad Sadegh Rasooli <rasooli.ms at gmail.com> Cc: corpora <corpora at uib.no>

Hi Mohammad,

I found http://code.google.com/p/mate-tools/ easy to use and extend.

Cheers, Mikhail

On Tue, Apr 24, 2012 at 12:53 PM, Mohammad Sadegh Rasooli < rasooli.ms at gmail.com> wrote:


> Dear corpora users,
>
> Is there any available dependency-based semantic role labeling annotation
> tool?
>
> Thanks
>
> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora
>
>
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 1219 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120424/5cb42aee/attachment.txt>

------------------------------

Message: 3 Date: Tue, 24 Apr 2012 15:47:24 +0430 From: Mohammad Sadegh Rasooli <rasooli.ms at gmail.com> Subject: Re: [Corpora-List] dependency-based semantic role labeling

annotation tool To: Mikhail Kozhevnikov <amblerr at gmail.com> Cc: corpora <corpora at uib.no>

Hello Mikhail,

I could not find an annotation tool in the mentioned page. All that I saw was parsing/lemmatization/tagging tools. Am I right?

Best,

On Tue, Apr 24, 2012 at 3:37 PM, Mikhail Kozhevnikov <amblerr at gmail.com>wrote:


> Hi Mohammad,
>
> I found http://code.google.com/p/mate-tools/ easy to use and extend.
>
> Cheers,
> Mikhail
>
> On Tue, Apr 24, 2012 at 12:53 PM, Mohammad Sadegh Rasooli <
> rasooli.ms at gmail.com> wrote:
>
>> Dear corpora users,
>>
>> Is there any available dependency-based semantic role labeling annotation
>> tool?
>>
>> Thanks
>>
>> _______________________________________________
>> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
>> Corpora mailing list
>> Corpora at uib.no
>> http://mailman.uib.no/listinfo/corpora
>>
>>
>
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 1863 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120424/f84630bf/attachment.txt>

------------------------------

Message: 4 Date: Tue, 24 Apr 2012 05:07:58 -0700 From: Asif Anjum <asif4605 at gmail.com> Subject: [Corpora-List] Request To: corpora at uib.no

Hi

i want a free software for Urdu language which can perform similar operations like antconc 3.2.1

Plz help in this regard -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 143 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120424/455166d0/attachment.txt>

------------------------------

Message: 5 Date: Tue, 24 Apr 2012 14:50:04 +0200 From: Mikhail Kozhevnikov <amblerr at gmail.com> Subject: Re: [Corpora-List] dependency-based semantic role labeling

annotation tool To: Mohammad Sadegh Rasooli <rasooli.ms at gmail.com> Cc: corpora <corpora at uib.no>

Hello Mohammad,

It's there. You can either download srl-3.tgz in the downloads section or check it out of the SVN as described in the source section. Then check the scripts folder there to see how to use the tools or, better yet, look into the code.

Cheers, Mikhail

On Tue, Apr 24, 2012 at 1:17 PM, Mohammad Sadegh Rasooli < rasooli.ms at gmail.com> wrote:


> Hello Mikhail,
>
> I could not find an annotation tool in the mentioned page. All that I saw
> was parsing/lemmatization/tagging tools. Am I right?
>
> Best,
>
>
> On Tue, Apr 24, 2012 at 3:37 PM, Mikhail Kozhevnikov <amblerr at gmail.com>wrote:
>
>> Hi Mohammad,
>>
>> I found http://code.google.com/p/mate-tools/ easy to use and extend.
>>
>> Cheers,
>> Mikhail
>>
>> On Tue, Apr 24, 2012 at 12:53 PM, Mohammad Sadegh Rasooli <
>> rasooli.ms at gmail.com> wrote:
>>
>>> Dear corpora users,
>>>
>>> Is there any available dependency-based semantic role labeling
>>> annotation tool?
>>>
>>> Thanks
>>>
>>> _______________________________________________
>>> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
>>> Corpora mailing list
>>> Corpora at uib.no
>>> http://mailman.uib.no/listinfo/corpora
>>>
>>>
>>
>
-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 2652 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120424/4573892f/attachment.txt>

------------------------------

Message: 6 Date: Tue, 24 Apr 2012 22:25:51 +0900 From: Laurence Anthony <anthony0122 at gmail.com> Subject: Re: [Corpora-List] Request To: corpora at uib.no

Hi,

What you will need is a program that can handle right-to-left languages. Unfortunately, AntConc cannot handle these languages now. It's a limitation of the programming language that I currently use.

I don't know of any freeware software that can do this, but a search for "bidi-awareness" might help you.

Laurence. -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 660 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120424/8f976f48/attachment.txt>

------------------------------

Message: 7 Date: Tue, 24 Apr 2012 16:09:24 +0200 From: Stefan Wermter <wermter at informatik.uni-hamburg.de> Subject: [Corpora-List] New International MSc Intelligent Adaptive

Systems To: "connectionists at cs.cmu.edu" <connectionists at cs.cmu.edu>,

euron-dist at iais.fraunhofer.de, list at ki-profs.de,

robotics-worldwide at usc.edu

New International MSc Programme "Intelligent Adaptive Systems"

A newly approved Master's programme "Intelligent Adaptive Systems" is offered by the University of Hamburg. The MSc IAS is a 2 year, research-oriented course taught fully in English. It starts October 1st, 2012 and students do not have to pay tuition fees. Requirements are a Bachelor degree related to Computer Science and proof of English language proficiency (TOEFL, IELTS, TELC, etc).

Application deadline: 11 May 2012 (for all students)

Homepage: http://www.master-intelligent-adaptive-systems.com Email: ias-info at informatik.uni-hamburg.de

Background: Intelligent systems and robots are expected to become an integral part of our daily lives. In order to be accepted by humans, intelligent systems have to adapt to changing environments as well as the users they interact with. Intelligent systems are not only expected to automatically acquire and manage knowledge through a variety of sensors but also to learn and optimise their behaviour over time. This International Master?s programme aims to provide students with the ability to build these intelligent adaptive systems and to prepare the students for a future market, where intelligent behaviour is considered the standard for computer systems.

Research-oriented, 2-year programme (4 semesters): The Master in Intelligent Adaptive Systems is a 2-year research-oriented programme that is taught in English. Students, both national and international, can benefit from an international environment and improve their grasp of the English language and knowledge on cultural differences. The selected modules provide a comprehensive overview including technical aspects and state-of-the art algorithms and methods. Students are introduced to current research in the corresponding fields and have the opportunity to deepen the acquired knowledge by participating in international research projects.

Curriculum: The Master?s programme is comprised of 120 credit points that are distributed between compulsory core lectures, selectable focus lectures, and project work: Core lectures include Software Architecture, Bio-Inspired AI, Intelligent Robotics, Neural Networks, Databases and Information Systems, Algorithmic Learning, Research Methods. 18 CP points can be chosen from focus modules (including natural language processing, image processing, robot technology, security and communication, and complex systems). Students can also choose 12 CP from other modules to extend their studies or deepen their knowledge in selected areas.

Application Requirements: We aim at offering the courses to a wide range of students. Applicants should have a strong background in computer science or a related field since programming and mathematical knowledge is assumed. In order to apply to the Master in Intelligent Adaptive Systems, you have to fulfil the following requirements:

a) A Bachelor degree in computer science or a related field insofar as 60 ECTS credit points were acquired in the field of computer science b) Proof of English language proficiency by (or comparable to): - CEFR/TELC Level C1 - IELTS 6.5 - TOEFL (IBT 100, PBT 575, CBT 220) - Cambridge CAE or CPE Next to these requirements, students have to provide a 2-page letter of motivation and a CV. More detailed information on application requirements and procedure can be found in the website http://www.master-intelligent-adaptive-systems.com

Further information can be found on the following pages: http://www.informatik.uni-hamburg.de/WTM/teaching/IntelligentAdaptiveSystems.shtml http://www.verwaltung.uni-hamburg.de/internationales/incoming_e.html http://www.verwaltung.uni-hamburg.de/internationales/interkuturell_e.html

Contact: University of Hamburg Department Informatics Knowledge Technology, WTM Vogt-Kölln-Straße 30 D - 22527 Hamburg, Germany Email: ias-info at informatik.uni-hamburg.de

Please forward to potentially interested students.

Sven Magg & Stefan Wermter

*********************************************** Professor Dr. Stefan Wermter Head of Knowledge Technology Department of Computer Science, WTM, Building F University of Hamburg Vogt Koelln Str. 30 22527 Hamburg, Germany

http://www.informatik.uni-hamburg.de/~wermter/ http://www.informatik.uni-hamburg.de/WTM/ ***********************************************

------------------------------

Message: 8 Date: Tue, 24 Apr 2012 16:52:18 +0200 From: "Kerstin Kunz" <k.kunz at mx.uni-saarland.de> Subject: [Corpora-List] WG: Job opening: professorship at Universität

des Saarlandes, Saarbrücken (Germany) To: <corpora at uib.no>

Von: Kerstin Kunz [mailto:k.kunz at mx.uni-saarland.de] Gesendet: Dienstag, 24. April 2012 16:45 An: 'corpora-bounces at uib.no' Betreff: Job opening: professorship at Universität des Saarlandes, Saarbrücken (Germany)

The Faculty of Linguistics, Literary and Cultural Studies (Humanities II) at Universität des Saarlandes, Saarbrücken (Germany) invites applications for a

Professorship (pay scale W3, tenured) in

Translation-Oriented Language Technology

The position is located at the Institute for Applied Linguistics, Translation and Interpreting (Fachrichtung 4.6: http://fr46.uni-saarland.de/) one of the few academic sites in Germany for translation studies with a special focus on language technology.

The successful candidate will be responsible for academic duties in research and teaching in translation-oriented language technology (machine/machine-aided translation, translation memories, terminology extraction and management, process management). Expertise in digital research infrastructures/e-humanities and/or empirical linguistic methods is desirable.

Candidates are required to have a proven record in acquiring and leading national and international research projects and are expected to contribute to the university’s research profile, both at the institute and the faculty as well as across faculties (e.g. collaboration with computational linguistics, informatics). In teaching, the successful candidate will be holding courses in translation technology (notably machine translation, translation memories, terminology management, process management, quality assurance) at both BA and MA levels. An ability to provide some coverage of Romance languages is desirable. Candidates are expected to contribute to further intra- and cross-faculty study programs. A working knowledge in German is expected.

Applicants are requested to submit their application, together with an academic CV, a record of their teaching experience, a list of academic publications, and copies of academic degree certificates.

Universität des Saarlandes is an equal opportunity employer. Applications of women are strongly encouraged for this type of position; applications of disabled persons will be given preferential treatment to those of other candidates with equal qualifications.

Applications should be sent to:

Universität des Saarlandes

Philosophische Fakultät II

Dekanat

Campus B3 1

66123 Saarbrücken

Germany

For the official and legally binding text (German) see <http://www.uni-saarland.de/campus/service-und-kultur/dienstleistungen-der-v erwaltung/stellenausschreibungen/wissenschaftliches-personal.html> http://www.uni-saarland.de/campus/service-und-kultur/dienstleistungen-der-ve rwaltung/stellenausschreibungen/wissenschaftliches-personal.html

The closing date for applications is 4 weeks after publication.

--------------------

Dr. Kerstin Kunz

Englische Übersetzungswissenschaft

FR 4.6 „Angewandte Sprachwissenschaft sowie Übersetzen und Dolmetschen"

Geb. A2.2, Campus

Universität des Saarlandes

D- 66123 Saarbrücken

Email: k.kunz at mx.uni-saarland.de

Tel.: +49(0)681-302-2563

-------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 9607 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120424/00e95ed5/attachment.txt> -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: W3-position-fr46-uds.txt URL: <https://mailman.uib.no/public/corpora/attachments/20120424/00e95ed5/attachment-0002.txt>

------------------------------

Message: 9 Date: Tue, 24 Apr 2012 16:55:24 +0200 From: anders bjorkelund <anders at ims.uni-stuttgart.de> Subject: Re: [Corpora-List] dependency-based semantic role labeling

annotation tool To: Mikhail Kozhevnikov <amblerr at gmail.com> Cc: corpora <corpora at uib.no>

Hi Mohammad,

Just for clarification, are you looking for a (statistical) system to parse semantic roles, or a tool (GUI) to create a gold standard annotation?

The system Mikhail refers to is a statistical trainable system. If you're looking for a tool to create a gold annotation, you might want to check out the tools used for creating PropBank: http://code.google.com/p/propbank/

Cheers, anders

On Tue, 2012-04-24 at 14:50 +0200, Mikhail Kozhevnikov wrote:
> Hello Mohammad,
>
> It's there. You can either download srl-3.tgz in the downloads section
> or check it out of the SVN as described in the source section. Then
> check the scripts folder there to see how to use the tools or, better
> yet, look into the code.
>
>
> Cheers,
> Mikhail
>
> On Tue, Apr 24, 2012 at 1:17 PM, Mohammad Sadegh Rasooli
> <rasooli.ms at gmail.com> wrote:
> Hello Mikhail,
>
> I could not find an annotation tool in the mentioned page. All
> that I saw was parsing/lemmatization/tagging tools. Am I
> right?
>
> Best,
>
>
> On Tue, Apr 24, 2012 at 3:37 PM, Mikhail Kozhevnikov
> <amblerr at gmail.com> wrote:
> Hi Mohammad,
>
>
> I found http://code.google.com/p/mate-tools/ easy to
> use and extend.
>
>
> Cheers,
> Mikhail
>
> On Tue, Apr 24, 2012 at 12:53 PM, Mohammad Sadegh
> Rasooli <rasooli.ms at gmail.com> wrote:
>
> Dear corpora users,
>
> Is there any available dependency-based
> semantic role labeling annotation tool?
>
> Thanks
>
>
>
> _______________________________________________
> UNSUBSCRIBE from this page:
> http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora
>
>
>
>
>
>
>
> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora

------------------------------

Message: 10 Date: Tue, 24 Apr 2012 17:16:15 +0200 From: Serge Heiden <slh at ens-lyon.fr> Subject: Re: [Corpora-List] Request To: corpora at uib.no

A non-text attachment was scrubbed... Name: not available Type: text/html Size: 3427 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120424/1ee66850/attachment.txt>

------------------------------

Message: 11 Date: Tue, 24 Apr 2012 12:03:52 -0400 From: maxwell <maxwell at umiacs.umd.edu> Subject: Re: [Corpora-List] Request To: Serge Heiden <slh at ens-lyon.fr> Cc: corpora at uib.no

On Tue, 24 Apr 2012 17:16:15 +0200, Serge Heiden <slh at ens-lyon.fr> wrote:
> Have a look at TXM 0.6 (free AND open-source):
> https://sourceforge.net/projects/txm [1]
> It handles right-to-left writing systems display*.
> You can check in the demo portal:
> http://txm.risc.cnrs.fr/demo/?locale=en [2]
> in which 'ONUAR' is a small sample UNO based arabic texts corpus.
> (build a lexicon, double-clic on a word line then double-clic
> on a KWIC line to get to the text edition)
>
> Best,
> Serge
> ____________________
>
> (*) Even if this is far from perfect (let alone the bad arabic
> tokenization, etc.).
> This is done nearly automagically by the technology we use
> (Java+Javascript GWT
> or Java Eclipse RCP/SWT for the desktop version)

In case anyone else is working on the Dhivehi language, there's a bug in Java which (as far as we have been able to discover) prevents proper rendering of the Thaana script used for Dhivehi. Thaana has long had a Unicode block, but Java seems not to recognize that Thaana is written right-to-left. The bug does not affect Arabic script. I've never checked about other right-to-left scripts, like Syriac.

Mike Maxwell

University of Maryland

------------------------------

Message: 12 Date: Tue, 24 Apr 2012 18:58:28 +0200 From: Eneko Agirre <e.agirre at ehu.es> Subject: [Corpora-List] *SEM 2012 Registration is now open To: undisclosed-recipients:;

*SEM-2012

June 7-8, Montreal, Canada

*SEM (pronounced STARSEM)

The first joint conference on

lexical and computational semantics

Collocated with NAACL-HLT 2012

http://ixa2.si.ehu.es/starsem

We are pleased to announce that the ACL special interest groups SIGLEX and SIGSEM are organising a joint conference on lexical and computational semantics: *SEM (STARSEM). The main goal of *SEM is to provide a stable forum for the growing number of NLP researchers working on different aspects of semantic processing, which has been scattered over a large array of small workshops and conferences. The first edition of *SEM will be a two-day conference collocated with the North American Chapter of the Association for Computational Linguistics and Human Language Technologies 2012 conference (NAACL HLT), which will take place in Montreal, Canada.

In addition, the conference will include parallel sessions on the following:

* presentations from organizers and participants of the shared task on Scope and Focus of Negation * presentations from organizers and participants of SemEval 2012

In order to check prices and register for *SEM, please visit the NAACL HLT conference website http://www.naaclhlt2012.org/registration/registration.php.

Note that registration for NAACL-HLT itself is optional, that is, you can register to *SEM only (or to NAACL-HLT only), or to both NAACL-HLT and *SEM.

Registration questions should be directed to Priscilla Rasmussen, acl--AT--aclweb.org

It is strongly suggested that hotel or student dorm accommodation arrangements be made very soon in our reserved blocks of rooms. The Grand Prix will commence the weekend following our conference and unused rooms may book up quickly with those participants.

We hope you will enjoy the conference and your time in Montreal!

Best

Eneko Agirre, General Chair Johan Bos, PC Co-chair Mona Diab, PC Co-chair e-mail: starsem-organizers at googlegroups com

------------------------------

Message: 13 Date: Tue, 24 Apr 2012 19:52:11 +0200 From: "Marc Brysbaert" <Marc.Brysbaert at UGent.be> Subject: [Corpora-List] age-of-acquisition norms for over 50 thousand

English words To: corpora at uib.no

We have collected age-of-acquisition (AoA) ratings for 31K English content words (nouns, verbs, adjectives). The collection of these new AoA norms was possible because we made use of the web-based crowdsourcing technology offered by the Amazon Mechanical Turk. Correlations with existing AoA measures suggest that these estimates are as good as the existing ones.

Because the Age-of-acquisition norms can also be used for inflected forms, we can expand the original list to a total of 51+K words, meaning that AoA can now be included in all word recognition studies (it still explains 5% of the variance in lexical decision times after word frequency, length, and OLD20 are controlled for).

You find various files with the ratings at http://crr.ugent.be/archives/806

Kuperman, V.,Stadthagen-Gonzalez, H., & Brysbaert, M. (in press). Age-of-acquisition ratings for 30 thousand English words. Behavior Research Methods.

----- End forwarded message -----

------------------------------

Message: 14 Date: Tue, 24 Apr 2012 14:18:07 -0400 From: Cristian Danescu-Niculescu-Mizil <cristian at cs.cornell.edu> Subject: [Corpora-List] Call for Papers: SocInfo 2012 (Lausanne,

Switzerland) To: <Corpora at uib.no>

Forth International Conference on Social Informatics (SocInfo 2012)

http://www.socinfo2012.com/

When: Dec 5, 2012 - Dec 7, 2012 Where: Lausanne, Switzerland Submission Deadline: Jul 7, 2012 Notification Due: Aug 31, 2012 Final Version Due: Sep 14, 2012

The International Conference on Social Informatics (SocInfo 2012) is an interdisciplinary venue for researchers from Computer Science, Informatics, Social Sciences and Management Sciences to share ideas and opinions, and present original research work on studying the interplay between socially-centric platforms and social phenomena. The ultimate goal of Social Informatics is to create better understanding of socially-centric platforms not just as a technology, but also as a set of social phenomena. To that end, we are inviting interdisciplinary papers, on applying information technology in the study of social phenomena, on applying social concepts in the design of information systems, on applying methods from the social sciences in the study of social computing and information systems, on applying computational algorithms to facilitate the study of social systems and human social dynamics, and on designing information and communication technologies that consider social context.

A special focus of SocInfo'2012 is on how technology can influence social phenomena through better motivation of human agents, through the use of social norms, through better modeling, or through a better understanding of social concepts like trust, credibility, privacy, and fairness. To this end we are especially inviting contributions demonstrating how behavioral theory can be formalized in agent-based models to study social dynamics. It is the expectation that this contributes to a further development of the social sciences with respect to studying and explaining various behavioral dynamics, such as opinion dynamics, social conflict, innovation diffusion, market dynamics, and crowd behavior. On the other hand, the creation of a coherent social behavioral model that is formulated as an agent system is a prerequisite for further development of socially-centric platforms and for the testing of new algorithms that use social concepts and attempt to realize social goals.

Thank you, Organizing Committee, SocInfo 2012

------------------------------

Message: 15 Date: Wed, 25 Apr 2012 07:36:51 +0200 (CEST) From: Michael Wiegand <Michael.Wiegand at lsv.uni-saarland.de> Subject: [Corpora-List] Call for Papers: Workshop on Practice and

Theory of Opinion Mining and Sentiment Analysis (Vienna, Austria) To: corpora at uib.no

------------------------------------------------------------- Apologies for multiple postings -------------------------------------------------------------

CALL FOR PAPERS

*PATHOS - Practice and Theory of Opinion Mining and Sentiment Analysis* workshop held in conjunction with KONVENS-2012

September 21, 2012, Vienna, Austria

Submission Deadline: June 15, 2012

Website: http://pathos.sentimental.li/

*Scope of the Workshop*

The goal of PATHOS is to attract researchers and developers in the area of sentiment analysis and opinion mining. The workshop focuses on (i) methods and resources for multi-lingual sentiment

analysis, (ii) dependencies of genre and domain in sentiment

analysis and its subtasks, (iii) sentiment analysis with distinction of emotional

categories, i.e. emotion analysis, and (iv) opinion holder and opinion target extraction.

While there is an abundance of methods and resources available for English, comparatively little research focuses on other languages or multi-lingual sentiment analysis. In addition to language differences, deviations across genres and domains require special treatment, but are so far only seldom taken into account. Emotion analysis goes beyond traditional sentiment analysis, giving insight into the different emotional categories of an opinionated statement. Thus it is not restricted to mere polarity identification but detects particular feelings, such as "fear", or "anger", "hope" and "joy". Opinion holder and target extraction is the domain in sentiment analysis with significant economic potential. It allows stakeholders to nail down the exact source and target of criticism or praise. Exploiting this knowledge helps improving products and services and can be considered a tool for quality assurance.

PATHOS will serve as a platform for these particular sub-areas of sentiment analysis.

The workshop will be organized by the recently founded Interest Group on German Sentiment Analysis: http://synergy.sentimental.li

*Topics of Interest*

We invite contributions on, but not necessarily limited to: - Genre- and domain-specific sentiment analysis - Cross-genre and cross-domain sentiment analysis - Semi-supervised/weakly supervised learning for sentiment analysis - Contrast of machine learning vs. linguistic approaches vs. hybrid

methods - Sentiment analysis on twitter and social media in general - Fine-to-coarse sentiment analysis - Emotion detection and classification - Representation of and calculus on emotions - Multi-lingual sentiment analysis - Lexical resources for opinion mining and sentiment analysis - Gold standards and methods for evaluation - Real-world applications and large-scale sentiment analysis - Trends and perspectives in the field

*Important Dates*

Paper submission deadline: June 15, 2012 Acceptance notification: July 20, 2012 Camera-ready version due: August 27, 2012 Workshop: September 21, 2012

*Submission Guidelines*

We will accept two types of submissions: full papers and short papers. The reviewing will be double blind. Each submission will be reviewed by at least 3 reviewers. All submissions should describe original work that has not been previously published. We also accept demos, position papers (opinion pieces), and submissions discussing interesting negative results, both as full and short papers. The submission guidelines of this workshop (w.r.t. the format of these types of papers) will follow the guidelines of the KONVENS 2012 main conference:

http://www.oegai.at/konvens2012/cfp.shtml To submit a paper, use the interface at: https://www.easychair.org/account/signin.cgi?conf=pathos2012

*Organizing committee*

Stefan Gindl (MODUL University Vienna, Austria) Robert Remus (University of Leipzig, Germany) Michael Wiegand (Saarland University, Germany)

*Program committee*

Alexandra Balahur (European Commission Joint Research Centre, Italy) Simon Clematide (University of Zuerich, Switzerland) Manfred Klenner (University of Zuerich, Switzerland) Johann Mitloehner (Vienna University of Economics and Business, Austria) Stefanos Petrakis (University of Zuerich, Switzerland) Josef Ruppenhofer (Hildesheim University, Germany) Swapna Somasundaran (Siemens Corporate Research, USA) Manfred Stede (Potsdam University, Germany) Ralf Steinberger (European Commission Joint Research Centre, Italy) Veselin Stoyanov (Johns Hopkins University, USA) Cigdem Toprak (Technische Universitaet Darmstadt, Germany) Ulli Waltinger (Siemens AG, Corporate Technology, Germany) Albert Weichselbraun (University of Applied Sciences Chur, Switzerland)

------------------------------

Message: 16 Date: Wed, 25 Apr 2012 00:26:00 -0700 (PDT) From: fatima zuhra <fateeshah at yahoo.com> Subject: Re: [Corpora-List] Request To: Asif Anjum <asif4605 at gmail.com> Cc: corpora at uib.no

Hi,

Xaira can be used for this purpose because it worked well for Pashto.

Fatima Tuz Zuhra

--- On Tue, 24/4/12, Asif Anjum <asif4605 at gmail.com> wrote:

From: Asif Anjum <asif4605 at gmail.com> Subject: [Corpora-List] Request To: corpora at uib.no Received: Tuesday, 24 April, 2012, 5:07 PM

Hi

i want a free software for Urdu language which can perform similar operations like antconc 3.2.1

Plz help in this regard

-----Inline Attachment Follows-----

_______________________________________________ UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora Corpora mailing list Corpora at uib.no http://mailman.uib.no/listinfo/corpora -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 1319 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120425/9d6a19c0/attachment.txt>

------------------------------

Message: 17 Date: Wed, 25 Apr 2012 12:06:51 +0430 From: Mohammad Sadegh Rasooli <rasooli.ms at gmail.com> Subject: Re: [Corpora-List] dependency-based semantic role labeling

annotation tool To: anders bjorkelund <anders at ims.uni-stuttgart.de> Cc: corpora <corpora at uib.no>

Hello,

Although a trainable code is needed for bootstrapping the treebank, my question is about a GUI tool for manual annotation.

Thanks

On 4/24/12, anders bjorkelund <anders at ims.uni-stuttgart.de> wrote:
> Hi Mohammad,
>
> Just for clarification, are you looking for a (statistical) system to
> parse semantic roles, or a tool (GUI) to create a gold standard
> annotation?
>
> The system Mikhail refers to is a statistical trainable system. If
> you're looking for a tool to create a gold annotation, you might want to
> check out the tools used for creating PropBank:
> http://code.google.com/p/propbank/
>
> Cheers,
> anders
>
> On Tue, 2012-04-24 at 14:50 +0200, Mikhail Kozhevnikov wrote:
>> Hello Mohammad,
>>

------------------------------

Message: 18 Date: Wed, 25 Apr 2012 11:02:53 +0300 From: Emad Mohamed <emohamed at umail.iu.edu> Subject: Re: [Corpora-List] dependency-based semantic role labeling

annotation tool To: Mohammad Sadegh Rasooli <rasooli.ms at gmail.com> Cc: corpora <corpora at uib.no>

I'm currently using brat, and it's a decent tool.

http://brat.nlplab.org/

On Wed, Apr 25, 2012 at 10:36 AM, Mohammad Sadegh Rasooli < rasooli.ms at gmail.com> wrote:


> Hello,
>
> Although a trainable code is needed for bootstrapping the treebank, my
> question is about a GUI tool for manual annotation.
>
> Thanks
>
> On 4/24/12, anders bjorkelund <anders at ims.uni-stuttgart.de> wrote:
> > Hi Mohammad,
> >
> > Just for clarification, are you looking for a (statistical) system to
> > parse semantic roles, or a tool (GUI) to create a gold standard
> > annotation?
> >
> > The system Mikhail refers to is a statistical trainable system. If
> > you're looking for a tool to create a gold annotation, you might want to
> > check out the tools used for creating PropBank:
> > http://code.google.com/p/propbank/
> >
> > Cheers,
> > anders
> >
> > On Tue, 2012-04-24 at 14:50 +0200, Mikhail Kozhevnikov wrote:
> >> Hello Mohammad,
> >>
>
> _______________________________________________
> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
> Corpora mailing list
> Corpora at uib.no
> http://mailman.uib.no/listinfo/corpora
>

-- Emad Mohamed aka Emad Nawfal Computational Linguist Telephone Number: 1 (510) 984 1108 -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 2146 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20120425/416d7fd3/attachment.txt>

---------------------------------------------------------------------- Send Corpora mailing list submissions to

corpora at uib.no

To subscribe or unsubscribe via the World Wide Web, visit

http://mailman.uib.no/listinfo/corpora or, via email, send a message with subject or body 'help' to

corpora-request at uib.no

You can reach the person managing the list at

corpora-owner at uib.no

When replying, please edit your Subject line so it is more specific than "Re: Contents of Corpora digest..."

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

End of Corpora Digest, Vol 58, Issue 30 ***************************************



More information about the Corpora mailing list