What's New!
  • Sept. 2, 2010
    		• : Slides of invited talks
  • July 16, 2010
    		• : Workshop program
  • July 8, 2010
    		• : Invited talks
  • July 2, 2010
    		• : List of accepted papers

    Background and Motivation

     A long-standing problem in Natural Language Processing has been a lack of large-scale knowledge for computers. The emergence of the Web and the rapid increase of information on the Web brought us to what could be called the "information explosion era," and drastically changed the environment of NLP. The Web is not only a marvelous target for NLP, but also a valuable resource from which knowledge could be extracted for computers. Motivated by the desire to have a very first opportunity to discuss early approaches to those issues and to share the state-of-the-art technologies at that time, the first International Workshop on NLP Challenges in the Information Explosion Era (NLPIX 2008) was successfully held in conjunction with WWW 2008 in Beijing.
    Since the discussion of the first workshop, research and development activities on large-scale text processing and large-scale knowledge acquisition become much more popular these days. The large-scale NLP naturally requires large-scale infrastructures, such as neatly-prepared huge corpora, robust morpho-syntactic tools, and high-performance computing environments. However, such infrastructures can not be prepared by individual researchers nor research groups alone in general, although of course we know some exceptions. Based on this motivation, towards much larger-scale NLP, activities aiming at constructing and sharing the infrastructures have continued. Although we have found many publications presented in recent conferences/workshops including the above mentioned workshop, we still do not have opportunities to compare latest approaches, share analysis on advantages/disadvantages, and discuss possible directions towards further improvement and innovation.
    Furthermore, beyond the success of large-scale NLP and knowledge acquisition, we are starting to face a new problem: how to manage and use the automatically acquired knowledge (AAK in short). We are still not confident that those large-scale AAK can actually solve real world problems. How to incorporate the AAK into existing NLP frameworks and how to manage them are yet unsolved issues. One approach could be some bootstrapping of extracting knowledge and enhancing NLP based on the knowledge. The representation and standardization of AAK are also emerging important issues. One of the most highly demanded applications for AAK-based NLP is a semantic search to cope with the information explosion on the Web. Though our daily life heavily depends on the Web information, our diversified needs have not been sufficiently satisfied by the existing search engines. AAK-based NLP can be a key technology to realize a new-generation semantic search, which incorporates enhanced information access, analysis and organization.

    Theme and Topics

    The aim of the second workshop of the series of International Workshop on NLP Challenges in the Information Explosion Era (NLPIX) is to bring researchers and practitioners together in order to discuss large-scale and sharable NLP infrastructures, and furthermore to discuss emerging NEW issues beyond them. Possible topics of the paper submissions include, but are not limited to:
    In particular, we solicit the papers that aim at fulfilling a NOVEL type of needs in Web access and that can provide a new insight into future directions of Web access research.

    Invited Talks

    Accepted Papers

    Workshop Schedule / Important Dates

    Registration

    Workshop Organizers

    Program Committee

    Previous NLPIX Workshop

    NLP Challenges in the Information Explosion Era (NLPIX 2008), at WWW2008 in Beijing, China.

    Contact Us