The 14th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL'2013) Hefei, Anhui, China, October 20-23, 2013

Special Session on Text Data Learning

Call for Papers

Overview

Tremendous efforts have been devoted to developing and applying different machine learning technologies to natural language text data, greatly expanding the fields of information retrieval and natural language processing, creating new areas of research. However, many challenges remain, such as:

  1. how we can successfully process different natural language related tasks with machine learning: ranking documents, classifying text, clustering, summarizing, analyzing, extracting information, and so on?
  2. how we can circumvent the barrier of lacking enough annotated data, despite the vast quantities of unannotated data?
  3. how we can adapt machine learning solutions across domains, genres, and languages?
  4. how we can make full use of the characteristics of text data in building machine learning based solutions?
  5. how we can create text learning systems to process Big Data in distributed and parallel environments?

This special session on text data learning will provide a forum for researchers and practitioners interested in information retrieval and natural language processing to exchange and report their latest findings in applying machine learning to understanding and mining natural language text data.

Topics of Interest

We invite researchers and practitioners to submit their original and unpublished work on all aspects of computational approaches to text data learning and their applications, including, but not limited to:

* Supervised, unsupervised and semi-supervised machine learning methods applied to managing, analyzing, understanding, mining, and exploiting text data in both normal and "big" scale

* Computational learning technologies adapted to processing text data across domain, genre, language, and scale

* Intelligent text data preparation, annotation and analysis for effectively learning

* Data representation for text learning and inference

* Novel applications of text data learning in Internet, social, enterprise and mobile environments

* Empirical and theoretical comparisons of text data learning methods including novel evaluation methods

We especially welcome submissions on learning methods considering the special characteristics of text data, e.g. sequential, structural, and graphical.

Submission

Please follow the IDEAL 2013 instructions for authors to prepare and submit your papers via the IDEAL 2013 online submission system. Please specify that your paper is for the Special Session on Text Data Learning. All accepted papers will be included in the IDEAL 2013 Proceedings, which will be published by Springer Verlag in the Lecture Notes on Computer Science Series, and indexed in EI and DBLP. Selected papers will be invited for special issues in several leading international journals in the field, including the International Journals of Neural Systems (IJNS) and Connection Science.

Important Dates

Paper Submission Deadline: 31 May 2013
Paper Submission Deadline: 10 June 2013
Notification of Acceptance:

5 July 2013
Camera-Ready Copy Due: 26 July 2013
Early Registration: 26 July 2013
Conference Presentation: 20-23 October 2013

Organisers

Baoli Li, Henan University of Technology, China (csblli at gmail.com)
Carl Vogel, Trinity College Dublin, Ireland (vogel at tcd.ie)

PC Members

Khurshid Ahmad, Trinity College Dublin, Ireland

Walter Daelemans, University of Antwerp, Belgium

Jinhua Du, Xi'An University of Technology, China

Martin Emms, Trinity College Dublin, Ireland

Moshe Koppel, Bar-Ilan University, Israel

Qin Lu, The Hong Kong Polytechnic University, Hong Kong

Saturnino Luz, Trinity College Dublin, Ireland

Xueqiang Lv, Beijing Information Science and Technology University, China

Erwan Moreau, Trinity College Dublin, Ireland

John Nerbonne, University of Groningen, The Netherlands

Brian Murphy, Carnegie Mellon University, USA

Saurav Sahay, Intel Labs, USA

Zhifang Sui, Peking University, China

Andreas Vlachos, University of Cambridge, UK

Dong Zhou, Hunan Univesity of Science and Technology, China