ACM SIGCHI General Interest Announcements (Mailing List)


Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Alessandro Moschitti <[log in to unmask]>
Reply To:
Alessandro Moschitti <[log in to unmask]>
Sat, 12 Feb 2011 11:02:00 -0700
text/plain (225 lines)
	                                     C A L L     f o r    P A P E R S

    	      Special Issue for the Journal of Natural Language  
Engineering on
  	    Statistical Learning of Natural Language Structured Input and  
(Apologies for multiple postings)

Machine learning and statistical approaches have become indispensable  
for large part of
Computational Linguistics and Natural Language Processing research. On  
one hand,
they have enhanced systems' accuracy and have significantly sped-up  
some design phases,
e.g. the inference phase. On the other hand, their use requires  
careful parameter tuning and,
above all, engineering of machine-based representations of natural  
language phenomena,
e.g. by means of features, which sometimes detach from the common  
sense interpretation of
such phenomena.

These difficulties become more marked when the input/output data have  
a structured and
relational form: the designer has both to engineer features for  
representing the system input,
e.g. the syntactic parse tree of a sentence, and devise methods for  
generating the output,
e.g. by building a set of classifiers, which provide boundaries and  
type (argument, function or
concept type) of some of the parse-tree constituents.

Research in empirical Natural Language Processing has been tackling  
these complexities
since the early work in the field, e.g. part-of-speech tagging is a  
problem in which the input
--word sequences-- and output --POS-tag sequences-- are structured.  
However, the models
initially designed were mainly based on local information. The use of  
such ad hoc solutions
was mainly due to the lack of statistical and machine learning theory  
suggesting how models
should be designed and trained for capturing dependencies among the  
items in the
input/output structured data. In contrast, recent work in machine  
learning has provided several
paradigms to globally represent and process such data: structural  
kernel methods, linear
models for structure learning, graphical models, constrained  
conditional models, and
re-ranking, among others.

However, none of the above approaches has been shown to be superior in  
general to the
rest. A general expressivity-efficiency trade off is observed, making  
the best option usually
task-dependant. Overall, the special issue is devoted to study  
engineering techniques for
effectively using natural language structures in the input and in the  
output of typical
computational linguistics applications. Therefore, the study on  
generalization of new or
traditional methods, which allow for fast design in different or novel  
NLP tasks is one important
aim of this special issue.

Finally, the special issue is also seeking for (partial) answers to  
the following questions:

   * Is there any evidence (empirical or theoretical) that can  
establish the superiority of one
     class of learning algorithms/paradigms over the others when  
applied to some concrete natural
     language structures?

   * When we use different classes of methods, e.g. SVMs vs CRFs, or  
different paradigms,
     what do we loose and what do we gain from a practical viewpoint  
(implementation, efficiency
     and accuracy)? This question is particularly interesting, when  
considering  different structure
     types: syntactic or semantic both shallow or deep.

   * Can we empirically demonstrate that theoretically motivated  
algorithms, e.g. SVM-struct,
      improve simpler models, e.g. re-ranking, in the NLP case?

   * Are there any other novel engineering approaches to NLP input and  
output structures?


For this special issue we invite submissions of papers describing  
novel and challenging work/results
in theories, models, applications or empirical studies on statistical  
learning for natural language
processing involving structured input and/or structured output.  
Therefore, the invited submission
must concern with (a) any kind of natural language problems; and (b)  
natural language structured

Assuming the target above, the range of topics to be covered will  
include, but will not be limited to
the following:

   * Practical and theoretical new learning approaches and architectures
   * Experimental evaluation/comparison of different approaches
   * Kernel Methods
   * Algorithms for structure output (batch and on–line):
     – structured SVMs, Perceptron, etc.
     – on sequences, trees, graphs, etc.
   * Bayesian Learning, Generative Models, Graphical Models
   * Relational Learning
   * Constraint Conditional models
   * Integer Linear Programming approaches
   * Graph-based algorithms
   * Ranking and Reranking
   * Scalability and effciency of ML methods
   * Robust approaches
     – noisy data, domain adaptation, small training sets, etc.
   * Unsupervised and semi-supervised models
   * Encoding of syntactic/semantic structures
   * Structured data encoding deep semantic information and relations
   * Relation between the syntactic and semantic layers in structured  


Call for papers: 	  		        30 November 2010
Submission of articles: 	  	        20 March 2011
Preliminary decisions to authors: 	26 June 2011
Submission of revised articles: 	28 August 2011
Final decisions to authors: 	  	23 October 2011
Final versions due from authors: 	27 November 2011


Articles submitted to this special issue must adhere to the NLE  
journal guidelines available at:

(see section "Manuscript requirements" for the journal latex style).

We encourage authors to keep their submissions below 30 pages.
Send your manuscript in pdf attached to an email addressed to [log in to unmask]
   - with subject filed: JNLE-SIO and
   - including names of the authors and title of the submission in the  

An alternative way to submit to JNLE-SIO is to submit a paper to  
TextGraph 6 and being selected
for contributing to JNLE. See the website:

The selected workshop papers must be extended to journal papers by  
following the indications of
both the TextGraph 6 reviewers and the JNLE-SIO editors. These  
upgraded versions have to be
submitted to JNLE-SIO no later than August 28, 2011 for the second  
round of review of JNLE-SIO.


Lluís Màrquez
TALP Research Center, Technical University of Catalonia
[log in to unmask]

Alessandro Moschitti
Information Engineering and Computer Science Department, University of  
[log in to unmask]


Roberto Basili, University of Rome, Italy
Ulf Brefeld, Yahoo!-Research, Spain
Razvan Bunescu, Ohio University, US
Nicola Cancedda, Xerox, France
Xavier Carreras, UPC, Spain
Stephen Clark, University of Cambridge, UK
Trevor Cohn, University of Sheffield, UK
Walter Daelemans, University of Antwerp, Belgium
Hal Daumé, University of Maryland, US
Jason Eisner, John Hopkins University, US
James Henderson, University of Geneva, Switzerland
Liang Huang, ISI, University of Southern California, US
Terry Koo, MIT CSAIL, US
Mirella Lapata, University of Edinburgh, UK
Yuji Matsumoto, Nara Institute of Science and Technology, Japan
Ryan McDonald, Microsoft Research, US
Raymond Mooney, University of Texas at Austin, US	
Hwee Tou Ng, National University of Singapore, Singapore
Sebastian Riedel, University of Massachusetts, US
Dan Roth, University of Illinois at Urbana Champaign, US
Mihai Surdeanu, Stanford University, US
Ivan Titov, Saarland University, Germany
Kristina Toutanova, Microsoft Research, US
Jun'ichi Tsujii, University of Tokyo, Japan
Antal van den Bosch, Tilburg University, The Netherlands
Scott Wen-tau Yih, Microsoft Research, US
Fabio Massimo Zanzotto, University of Rome "Tor Vergata", Italy
Min Zhang, A-STAR, Singapore

                To unsubscribe, send an empty email to
     mailto:[log in to unmask]
    For further details of CHI lists see