Preliminary Schedule

8:45-9:00	Introduction
9:00-10:00	Invited Talk: Andrew McCallum
10:00-10:25	Analysis of the Wikipedia Category Graph for NLP Applications Torsten Zesch and Iryna Gurevych
10:30-11:00	COFFEE BREAK
11:00-11:25	Multi-level Association Graphs - A New Graph-Based Model for Information Retrieval Hans Friedrich Witschel
11:25-11:50	Extractive Automatic Summarization: Does more linguistic knowledge make a difference? Daniel S. Leite, Lucia H. M. Rino, Thiago A. S. Pardo and Maria das Gracas V. Nunes
11:50-12:15	Timestamped Graphs: Evolutionary Models for Multi-document Text Summarization Ziheng Lin and Min-Yen Kan
12:15-12:30	Unigram Language Models using Diffusion Smoothing over Graph Bruno Jedynak and Damianos Karakos
12:30-14:00	LUNCH BREAK
14:00-14:25	Transductive Structured Classification through Constrained Min-Cuts Kuzman Ganchev and Fernando Pereira
14:25-14:50	Latent Semantic Grammar Induction: Context, Projectivity, and Prior Distributions Andrew M Olney
14:50-15:15	Learning to Transform Linguistic Graphs Valentin Jijkoun and Maarten de Rijke
15:15-15:30	Semi-supervised Algorithm for Human-Computer Dialogue Mining Calkin S. Montero and Kenji Araki
15:30-16:00	COFFEE BREAK
16:00-16:25	Correlations in the organization of large-scale syntactic dependency networks Ramon Ferrer i Cancho, Alexander Mehler, Olga Pustylnikov and Albert Diaz-Guilera
16:25-16:50	DLSITE-2: Semantic Similarity Based on Syntactic Dependency Trees Applied to Textual Entailment Daniel Micol, Oscar Ferrández, Rafael Munoz and Manuel Palomar
16:50-17:15	How Difficult is it to Develop a Perfect Spell-checker? A Cross-linguistic Analysis through Complex Network Approach Monojit Choudhury, Markose Thomas, Animesh Mukherjee, Anupam Basu and Niloy Ganguly
17:15-17:30	Vertex Degree Distribution for the Graph of Word Co-Occurrences in Russian Victor Kapustin and Anna Jamsen
17:30-18:00	Open discussion: Where we are, where are we going?

Call for Papers

Recent years have shown an increased interest in bringing the field of graph theory into 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, ranging from part of speech tagging, word sense disambiguation and parsing to information extraction, semantic role assignment, summarization and sentiment analysis.

This workshop builds on the success of the first TextGraphs workshop at HLT-NAACL 2006. The aim of this workshop is to bring together researchers working on problems related to the use of graph-based algorithms for natural language processing and on the theory of graph-based methods. It will address a broader spectrum of research areas to foster exchange of ideas and help to identify principles of using the graph notions that go beyond an ad-hoc usage. Unveiling these principles will give rise to applying generic graph methods to many new problems that can be encoded in this framework.

We invite submissions of papers on graph-based methods applied to NLP-related problems. Topics include, but are not limited to:

• Graph representations for ontology learning and word sense disambiguation
• Graph algorithms for Information Retrieval, text mining and understanding
• Graph matching for Information Extraction
• Random walk graph methods and Spectral graph clustering
• Graph labeling and edge labeling for semantic representations
• Encoding semantic distances in graphs
• Ranking algorithms based on graphs
• Small world graphs in natural language
• Semi-supervised graph-based methods
• Statistical network analysis and methods for NLP

Organization Committee

Chris Biemann, U. Leipzig, biem at informatik.uni-leipzig.de
Irina Matveeva, U. Chicago, matveeva at cs.uchicago.edu
Rada Mihalcea, U. North Texas, rada at cs.unt.edu
Dragomir Radev, U. Michigan, radev at umich.edu

Program Committee

Eneko Agirre, University of the Basque Country
Monojit Choudhury, Indian Institute of Technology
Diane Cook, Washington State University
Hal Daume III, University of Utah
Gael Dias, Beira Interior University
Gunes Erkan, University of Michigan
Michael Gamon, Microsoft Research
Bruno Gaume, IRIT
Andrew Goldberg, University of Wisconsin
Hany Hassan, IBM Egypt
Samer Hassan, University of North Texas
Rosie Jones, Yahoo Research
Andrew McCallum, University of Massachusetts
Ani Nenkova, Stanford University
Patrick Pantel, USC Information Sciences Institute
Uwe Quasthoff, University of Leipzig
Aitor Soroa, University of the Basque Country
Simone Teufel, Cambridge University
Kristina Toutanova, Microsoft Research
Lucy Vanderwende, Microsoft Research
Dominic Widdows, Maya Design
Florian Wolf, F-W Consulting
Fabio Massimo Zanzotto, University of Rome "Tor Vergata"
Xiaojin Zhu, University of Wisconsin

Important Dates

Regular paper submissions	January 29
Short paper submissions	February 4
Notification of acceptance	February 22
Camera-ready papers	March 1
Workshop	April 26

Author Instructions

Submissions will consist of regular full papers of max. 8 pages and short papers of max. 4 pages, formatted following the NAACL 2007 formatting guidelines. Papers should be submitted using the online submission form. For any questions, please contact one of the organizers.