One-paragraph descriptions of the accepted Thematic Sessions of The 1st International Joint Conference of Natural Language Processing appear below.


1. Natural Language Learning using Both Labeled and Unlabeled Data

Organizer : Hang Li (Microsoft Research Asia, Beijing)

Recently, a new trend has arisen in the field of Natural Language Processing (NLP): the development of machine learning technologies that use both labeled and unlabeled data for training. Methods that have been proposed under this paradigm include co-training, EM learning, transductive learning, and other semi-supervised learning techniques. For many NLP tasks, existing data are by their nature unlabeled and manually labeling them is prohibitively expensive. Effective utilization of both unlabeled and labeled data in learning is also a challenging but important issue. The goal of this thematic session is to bring together researchers working on this issue from different perspectives, in order to share their latest research results and to discuss future directions. We think that this session will advance research not only in exploiting unlabeled data but also in other natural language learning issues.


2. Natural Language Technology in the Text Processing User Interface

Organizers: Michael Kuehn (Universitaet Koblenz-Landau, Koblenz)
and Kumiko Tanaka-Ishii (University of Tokyo, Tokyo)

The emergence of applications like mobile text processing, communication aids and authoring support require sophisticated methods of text processing under challenging conditions. We invite researchers to discuss language technologies such as (but not restricted to) language modeling, analysis, summarization and disambiguation, in order to assist the user at the text processing front-end.


3. Mobile Information Retrieval

Organizer: Mun-Kew Leong (Institute for Infocomm Research, Singapore)

One of the strongest impacts in recent information technology is the way mobility has changed computer applications. The rapid rate of handphone adoption, the ubiquitous PDA, and the low cost of wireless adoption has created new problems, new challenges, and new opportunities to researchers in many disciplines. One common thread through all these applications is the necessity for information retrieval in one form or another. Another characteristic is the limited screen size of mobile devices and the consequent ramifications on input and output. The use of NLP plays an integral part in creating better user interfaces, better analysis of results for precise display, and greater understanding in the iterative interaction (dialogue) between user and mobile device. We propose this workshop to explore user oriented and theoretical limits and characteristics of NLP and IR within the context of mobile devices.


4. Text mining in Biomedicine

Organizers: Sophia Ananiadou (Salford University, Manchester)
Jong C. Park (Kaist, Daejeon)

With biomedical literature expanding so rapidly, there is an urgent need to discover and organise knowledge extracted from texts. Although factual databases contain crucial information the overwhelming amount of new knowledge remains in textual form (e.g. MEDLINE). In addition, new terms are constantly coined as the relationships linking new genes, drugs, proteins etc. As the size of biomedical literature is expanding, more systems are applying a variety of methods to automate the process of knowledge acquisition and management. These include a variety of techniques such as statistics, machine learning, SVMs, deep or shallow linguistic or domain knowledge etc. Some NLP related topics are challenging in biomedicine such as: dynamic terminology management, named-entity recognition , integration with non-textual resources, discovery of named relationships, populating and updating existing ontologies / taxonomies. The aim of this thematic session is to examine issu es and challenges in the area of biomedical text mining.