CALL FOR PAPERS
TextGraphs-11: Graph-based Methods for Natural Language Processing
Workshop at the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017)
Vancouver, Canada
http://www.textgraphs.org/ws17
WORKSHOP DESCRIPTION
For the past eleven years, the workshops in the TextGraphs series
have published and promoted the synergy between the field of Graph
Theory (GT) and Natural Language Processing (NLP). The eleventh edition
of the TextGraphs workshop aims to extend the focus on issues and
solutions for large-scale graphs, such as those derived for web- scale
knowledge acquisition or social networks. We plan to encourage the
de-scription of novel NLP problems or applications that have emerged in
recent years, which can be addressed with existing and new graph-based
methods. Furthermore, we will also encourage research on applications of
graph-based methods in the area of Semantic Web in order to link them
to related NLP problems and applications.
The target audience comprises researchers working on problems
related to either Graph Theory or graph-based algorithms applied to
Natural Language Processing, social media, and the Semantic Web.
SPECIAL TOPIC
In a novel and exciting extension, we will encourage graph-based
interpretations of deep learning models for NLP tasks. Though deep
learning models are displaying state-of-the-art performance on many NLP
tasks, they are often criticized for not being interpretable (due to
their various layers and large number of parameters). In the
TextGraphs-11 workshop we will introduce a new challenge for graph-based
methods: the development of methods for reasoning and interpretation of
the layers used in deep learning models. Given that a neural network
is, from one point of view, nothing but a graph through which activation
scores are propagated, many of the existing graph-based methods used in
our workshop community could potentially apply. Can a graph-based
perspective help provide insights for making deep processing
comprehensible for humans and computers? What are the capabilities and
limits when graph-based methods are applied to neural networks in
general? Which aspects of the networks are not susceptible to such
treatment, and why not?
WORKSHOP TOPICS
TextGraphs-11 invites submissions on (but not limited to) the following topics:
* Graph-based methods for providing reasoning and interpretation of deep learning methods
* Graph-based methods for reasoning and interpreting deep processing by neural networks,
* Explorations of the capabilities and limits when graph-based methods are applied to neural networks,
* Investigation of which aspects of neural networks are not amenable to graph-based methods.
* Graph-based methods for Information Retrieval, Information Extraction, and Text Mining
* Graph-based methods for word sense disambiguation,
* Graph-based representations for ontology learning,
* Graph-based strategies for semantic relations identification,
* Encoding semantic distances in graphs,
* Graph-based techniques for text summarization,simplification,and paraphrasing,
* Graph-based techniques for document navigation and visualization,
* Reranking with graphs,
* Applications of label propagation algorithms, etc.
* New graph-based methods for NLP applications, and novel use of existing graph methods for new NLP tasks
* Random walk methods in graphs,
* Spectral graph clustering,
* Semi-supervised graph-based methods,
* Methods and analyses for statistical networks,
* Small world graphs,
* Dynamic graph representations,
* Topological and pre-topological analysis of graphs,
* Graph kernels, etc.
* Graph-based methods for applications on social networks
* Rumor proliferation,
* E-reputation,
* Multiple identity detection,
* Language dynamics studies,
* Surveillance systems, etc.
* Graph-based methods for NLP and Semantic Web
* Representation learning methods for knowledge graphs (e.g., knowledge graph embedding),
* Using graphs-based methods to populate ontologies using textual data,
* Inducing knowledge of ontologies into NLP applications using graphs,
* Merging ontologies with graph-based methods using NLP techniques.
IMPORTANT DATES
All submission deadlines are at 11:59 p.m. PST
Paper submission: April 21, 2017
Notification of acceptance: May 19, 2017
Camera-ready submission: May 26, 2017
Workshop date: August 3 or 4, 2017
SUBMISSION
TextGraphs-11 solicits both long and short paper submissions.
Long paper submissions must describe substantial, original,
completed and unpublished work. Wherever appropriate, concrete
evaluation and analysis should be included. Long papers may consist of
up to eight (8) pages of content, plus two pages of references. Final
versions of long papers will be given one additional page of content (up
to 9 pages) to address reviewers’ remarks.
Short paper submissions must describe original and unpublished work.
Please note that a short paper is not a shortened long paper. Instead
short papers should have a point that can be made in a few pages. Short
papers may consist of up to four (4) pages of content, plus one page of
references. Upon acceptance, short papers will also be given one
additional content page (up to 5 content pages) in the proceedings.
Both long and short paper submissions must follow the two-column
format of ACL 2017 proceedings. We strongly recommend the use of ACL
LaTeX style files tailored for ACL 2017 conference. Submissions must
conform to the official style guidelines, which are contained in the
style files, and they must be in PDF format. Style files and other
information about paper formatting requirements can be found at the ACL
2017 website.
Submission is electronic, using the SoftConf START conference management system:
https://www.softconf.com/acl2017/textgraphs/
BEST PAPER AWARD
The Program Committee will select a best paper submitted to
TextGraphs-11. The authors of the best manuscript will receive the
valuable Best Paper Award. Both long and short submissions will be taken
in consideration for the Best Paper Award.
PROGRAM COMMITTEE (in alphabetic order)
* Sivaji Bandyopadhyay, Jadavpur University, Kolkata, India
* Pushpak Bhattacharyya, IIT Bombay, India
* Chris Biemann, University of Hamburg, Germany
* Tanmoy Chakraborty, University of Maryland, USA
* Asif Ekbar, Indian Institute of Technology, Patna, India
* Marc Franco Salvador, University of Valencia, Spain
* Ioana Hulpus, University of Mannheim, Germany
* Roman Klinger, University of Stuttgart, Germany
* Nikola Ljubesǐć, University of Zagreb, Croatia
* Hećtor Martínez Alonso, Inria & University Paris Diderot, France
* Gabor Melli, VigLink, USA
* Rada Mihalcea, University of Michigan, USA
* Alessandro Moschitti, University of Trento, Italy
* Animesh Mukherjee, IIT Kharagpur, India
* Vivi Nastase, Heidelberg University, Germany
* Roberto Navigli, “La Sapienza” University of Rome, Italy
* Alexander Panchenko, University of Hamburg, Germany
* Simone Paolo Ponzetto, University of Mannheim, Germany
* Steffen Remus, University of Hamburg, Germany
* Stephan Roller, UT Austin, USA
* Shourya Roy, Xerox Research, India
* Anders Søgaard, University of Copenhagen, Denmark
* Jan Sňajder, University of Zagreb, Croatia
* Aline Villavicencio, F. University of Rio Grande do Sul, Brazil
* Ivan Vulić, University of Cambridge, United Kingdom
* Fabio Massimo Zanzotto, “Tor vergata” University of Rome, Italy
ORGANIZERS
Martin Riedl, University of Hamburg
riedl@informatik.uni-hamburg.de
Swapna Somasundaran, Educational Testing Services
ssomasundaran@ets.org
Goran Glavaš, University of Mannheim
goran@informatik.uni-mannheim.de
Eduard Hovy, Carnegie Mellon University
hovy@cmu.edu
