NAACL-HLT 07 logo

Home Page
Important Dates

Conference Program
Doctoral Consortium

Local Arrangements
Conference Registration
Reception and Banquet
Hotel Accommodations
For Presenters
About Rochester
Student Volunteers
Visa Information

Conference Organizers

Calls for Participation
Call for Papers
Call for Demos
Call for Tutorials
Call for Workshops
Submission Format
Online Submissions
NAACL HLT 2007 Workshops

Accepted Workshops

The following workshops have been accepted to NAACL HLT 2007: All workshops take place on April 26 (DUC continues to April 27).

Document Understanding Conference (DUC) 2007

The Document Understanding Conference (DUC) is a series of summarization evaluations that have been conducted by the National Institute of Standards and Technology (NIST) since 2001. Its goal is to further progress in automatic text summarization and enable researchers to participate in large-scale experiments in both the development and evaluation of summarization systems. DUC 2007 has two system tasks: The main task is to produce 250-word summaries of multiple documents in answer to a complex question; the update summary task is to produce short summaries of newswire articles under the assumption that the user has already read a set of earlier articles. The workshop will include the results of the DUC 2007 evaluation, papers from task participants, and discussion of future tasks.


  • Hoa Trang Dang, NIST
  • Donna Harman, NIST

Workshop Home Page:

Computational Approaches to Figurative Language

Figurative language, such as metaphor, metonymy, idioms, among others, is in abundance in natural discourse. The recognition of figurative language use and the computation of figurative language meaning constitute one of the hardest problems for a variety of natural language processing tasks, such as machine translation, text summarization, and question answering. As natural language processing moves to an unprecedented new stage, it has become more urgent than ever to tackle the bottleneck presented by figurative language. This workshop will provide a venue for researchers in this area to inform each other and the natural language processing community at large of the state of the art of current systems and to reach a better understanding of the new issues and challenges that need to be tackled.


  • Xiaofei Lu, Pennsylvania State University
  • Anna Feldman, Montclair State University

Workshop Home Page:

TextGraphs-2: Graph-based Methods for Natural Language Processing

In many NLP applications entities can be naturally represented as nodes in a graph and relations between them can be represented as edges. Recent research has shown that graph-based representations of linguistic units as diverse as words, sentences and documents give rise to novel and efficient solutions in a variety of NLP tasks. This workshop focuses on graph-based algorithms for natural language processing and on the theory of graph-based methods.


  • Chris Biemann, University of Leipzig
  • Irina Matveeva, University of Chicago
  • Rada Mihalcea, University of North Texas
  • Dragomir Radev, University of Michigan

Workshop Home Page:

Bridging the Gap: Academic and Industrial Research in Dialog Technologies

In the past decade, we have seen a rapid increase of dialog systems in various industrial applications, including telephone-based services, in-car interaction systems, internet-based customer support, talking characters in computer games, and mobile devices. Industry-driven standards, such as VoiceXML, are also becoming popular. While there has been an increased amount of effort in dialog technology research in the academic world, progress from such academic research has not benefited the real world applications to a satisfactory extent. The purpose of this one day workshop is to provide a forum to bring industrial and academic researchers together to share their experiences and visions in the dialog technology development, and to identify topics that are of interest to both camps.


    Fuliang Weng, Research and Technology Center, Robert Bosch Corporation
    Ye-Yi Wang, Microsoft Research, Microsoft Corporation
    Gokhan Tur, Speech Lab, SRI International
    Junling Hu, Research & Technology Center, Robert Bosch Corporation

Workshop Home Page:

Syntax and Structure in Statistical Translation (SSST)

Tree-structured mappings between languages are widely recognized as desirable for statistical machine translation, and there is mounting interest in approaches built on a family of formalisms that includes synchronous/transduction grammars and their tree transducer equivalents. From this formal basis, there has been rapid progress on many different fronts, ranging from purely mathematical results to very strong showings in large-scale evaluations. The workshop on Syntax and Structure in Statistical Translation seeks to bring together researchers working on diverse aspects of synchronous/transduction grammars in relation to statistical machine translation, to build stronger connections in this area and stimulate further progress.


  • Dekai Wu, HKUST
  • David Chiang, ISI/USC

Workshop Home Page:

Workshop Co-Chairs:

  • James Allan, U Massachusetts
  • Marti Hearst, UC Berkeley
  • Gina-Anne Levow, U Chicago
For inquiries, send email to: hlt-naacl07-workshops at

hlt-webadmin @ cs rochester edu October 20, 2006