|
Workshop at EMNLP-IJCNLP, Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (November 3–7, 2019) in Hong Kong
Date: November 3 or November 4, 2019
Location: Hong Kong
!!! We are excited to announce a shared task for this year’s workshop (see details below) !!!
Website: https://sites.google.com/view/textgraphs2019
# WORKSHOP DESCRIPTION
The TextGraphs series of workshops, now going on for more than a decade, have published and promoted the synergy between the field of Graph Theory (GT) and Natural Language Processing (NLP).
The thirteenth edition of the TextGraphs workshop aims to extend the focus on graph-based and graph-supported machine learning and deep learning methods. We encourage the description 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 also encourage research on applications of multi-hop inference and 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.
# WORKSHOP TOPICS
TextGraphs invites submissions on (but not limited to) the following topics (see the website for a full list):
* Graph embeddings
* Graph-based and graph-supported deep learning (e.g., graph-based recurrent and recursive networks)
* Probabilistic graphical models and structure learning methods
* Graph-based methods for reasoning and interpreting deep neural networks
* Exploration of capabilities and limitations of graph-based methods being applied to neural networks
* Investigation of aspects of neural networks that are (not) susceptible to graph-based analysis
* Graph-based methods for Information Retrieval, Information Extraction, and Text Mining
* Graph-based methods for word sense disambiguation
* Graph-based strategies for semantic relation identification
* Encoding semantic distances in graphs
* Graph-based techniques for text summarization, simplification, and paraphrasing
* Graph-based techniques for document navigation and visualization
* New graph-based methods for NLP applications
* Random walk methods in graphs
* Spectral graph clustering
* Semi-supervised graph-based methods
* Small world graphs
* Dynamic graph representations
* Graph kernels
* Graph-based methods for applications on social networks
* Graph-based methods for NLP and Semantic Web
* Inducing knowledge of ontologies into NLP applications using graphs
# IMPORTANT DATES
All submission deadlines are at 11:59 p.m. PST
Paper submission: August 23, 2019
Notification of acceptance: September 16, 2019
Camera-ready submission: September 30, 2019
Workshop date: November 3 or 4, 2019
# SUBMISSION
TextGraphs 2019 solicits both long and short paper submissions (more details on https://sites.google.com/view/textgraphs2019/).
Submission is electronic, using the SoftConf START conference management system:
https://www.softconf.com/emnlp2019/ws-TextGraphs-2019
# SHARED TASK: EXPLANATION REGENERATION
We are excited to announce a shared task on Explanation Regeneration! The resulting papers will be peer-reviewed by participating teams, and accepted system descriptions will be presented along with the main workshop papers.
Multi-hop inference is the task of combining more than one piece of information to solve an inference task, such as question answering. The shared task on Explanation Regeneration asks participants to develop methods to reconstruct gold explanations for elementary science questions, using a new corpus of gold explanations that provides supervision and instrumentation for this multi-hop inference task.
This shared task focuses on explanation reconstruction, a stepping-stone towards general multi-hop inference over language. In particular, the inputs to this task consist of questions and their correct answers. Participating systems must extract and rank explanation sentences from a provided structured knowledge base such that the top-ranked sentences provide a complete explanation for the given answer.
## Example
For example, for the question: "Which of the following is an example of an organism taking in nutrients?" with the correct answer: "a girl eating an apple", an ideal system would rank the following explanatory statements at the top of its extracted sentences:
1. A girl means a human girl.
2. Humans are living organisms.
3. Eating is when an organism takes in nutrients in the form of food.
4. Fruits are kinds of foods.
5. An apple is a kind of fruit.
The data used in this shared task contains 1,680 questions, together with explanation sentences for their correct answers (Jansen et al., 2018).
The knowledge base supporting these questions contains approximately 5,000 facts.
Please see the shared task website for more details: https://github.com/umanlp/tg2019task
Competition on CodaLab: https://competitions.codalab.org/competitions/20150
## Important Dates for Shared Task
13-05-2019: Example (trial) data release
17-05-2019: Training data release
12-07-2019: Test data release; Evaluation start
09-08-2019: Evaluation end
23-08-2019: System description paper deadline
11-09-2019: Deadline for reviews of system description papers
16-09-2019: Author notifications
30-09-2019: Camera-ready description paper deadline
03-11-2019/04-11-2019: TextGraphs-13 workshop
# PROGRAM COMMITTEE
Željko Agić, IT University of Copenhagen, Denmark
Tomáš Brychcín, University of West Bohemia, Czech Republic
Flavio Massimiliano Cecchini, Università Cattolica del Sacro Cuore, Italy
Tanmoy Chakraborty, Indian Institute of Technology Delhi, India
Mihail Chernoskutov, Krasovskii Institute of Mathematics and Mechanics, Russia
Stefano Faralli, University of Rome Unitelma Sapienza, Italy
Michael Flor, Educational Testing Service, USA
Sorcha Gilroy, University of Edinburgh, UK
Carlos Gómez-Rodríguez, Universidade da Coruña, Spain
Tomáš Hercig, University of West Bohemia, Czech Republic
Anne Lauscher, University of Mannheim, Germany
Suman Kalyan Maity, Northwestern University, USA
Fragkiskos Malliaros, École Centrale, France
Gabor Melli, Sony PlayStation, USA
Mohsen Mesgar, Ubiquitous Knowledge Processing (UKP) Lab, Germany
Clayton Morrison, University of Arizona, USA
Animesh Mukherjee, Indian Institute of Technology Kharagpur, India
Giannis Nikolentzos, École Polytechnique, France
Enrique Noriega-Atala, University of Arizona, USA
Simone Paolo Ponzetto, University of Mannheim, Germany
Jan Wira Gotama Putra, Tokyo Institute of Technology, Japan
Natalie Schluter, IT University, Danmark
Rebecca Sharp, University of Arizona, USA
Konstantinos Skianis, École Polytechnique, France
Nicolas Turenne, Université Paris-Est Marne-la-Vallée, France
Kateryna Tymoshenko, University of Trento, Italy
Ivan Vulić, University of Cambridge, UK
Vikas Yadav, University of Arizona, USA
Rui Zhang, Yale University, USA
# ORGANIZERS
Dmitry Ustalov, University of Mannheim
Peter Jansen, University of Arizona
Swapna Somasundaran, Educational Testing Service
Goran Glavaš, University of Mannheim
Martin Riedl, University of Stuttgart
Mihai Surdeanu, University of Arizona
Michalis Vazirgiannis, Ecole Polytechnique
# CONTACT
Please direct all questions and inquiries to our official e-mail address ([email protected]) or contact any of the organizers via their individual emails.
Connect with us on social media:
* Join us on Facebook: https://www.facebook.com/groups/900711756665369/
* Follow us on Twitter: https://twitter.com/textgraphs
* Join us on LinkedIn: https://www.linkedin.com/groups/4882867
|
