OLP2 - 2nd Workshop on Ontology Learning and Population

Bridging the Gap between Text and Knowledge

Workshop at COLING/ACL 2006

July 22nd, 2006

Sydney, Australia

Program

 

Download Proceedings

 

Download Presentations

Supported By

 

 

9:00 – 9:30

Paul Buitelaar, Philipp Cimiano, Berenike Loos

Introduction to OLP and Overview of the Workshop

 

Session 1

Lexical Ontology Enrichment

 

9:30 – 10:00

Roberto Navigli and Paola Velardi

Enriching a Formal Ontology with a Thesaurus: an Application in the Cultural Heritage Domain

 

10:00 – 10:30

Eric Nichols, Francis Bond, Takaaki Tanaka, Fujita Sanae and Dan Flickinger

Multilingual Ontology Acquisition from Multiple MRDs

 

10:30 – 11:00

Coffee Break

 

Session 2

Ontology Population and Ontology-Based IE

 

11:00 – 11:30

Fabian Suchanek, Georgiana Ifrim and Gerhard Weikum

LEILA: Learning to Extract Information by Linguistic Analysis

 

11:30 – 12:00

Bernardo Magnini, Emanuele Pianta, Octavian Popescu and Manuela Speranza

Ontology Population from Textual Mentions: Task Definition and Benchmark

 

12:00 – 12:30

Koen Deschacht and Marie-Francine Moens

Efficient Hierarchical Entity Classifier Using Conditional Random Fields

 

12:30 – 14:00

Lunch Break

 

Session 3

Taxonomy and Relation Extraction

 

14:00 – 14:30

Pum-Mo Ryu and Key-Sun Choi

Taxonomy Learning using Term Specificity and Similarity

 

14:30 – 15:00

Enrique Alfonseca, Maria Ruiz-Casado, Manabu Okumura and Pablo Castells

Towards Large-scale Non-taxonomic Relation Extraction: Estimating the Precision of Rote Extractors

 

15:00 – 15:30

Lucia Specia and Enrico Motta

A hybrid approach for extracting semantic relations from texts

 

15:30 – 16:00

Coffee Break

 

16:00 – 17:45

Panel Discussion and Invited Talks by Johan Bos (Universita di Roma, Italy) and Dekang Lin (Google, USA)

 

Topics:

 

- What are the important challenges in ontology learning?

- What are the tasks or applications in which ontologies and background knowledge show a clear potential for improvement of results?

- How advanced is the state-of-the-art in ontology learning / knowledge acquisition to support these applications or tasks?

 

17:45 – 18:00

Concluding Remarks

 

Topic and Motivation

 

 

An ontology is an explicit and formal specification of a shared conceptualization of a domain of interest. Ontologies formalize the intensional aspects of a domain, whereas the extensional part is provided by a knowledge base that contains assertions about instances of concepts and relations as defined by the ontology. The process of defining and instantiating a knowledge base is referred to as knowledge markup or ontology population, whereas (semi-)automatic support in ontology development is usually referred to as ontology learning.


Ontologies have been broadly used in knowledge management applications, including Semantic Web applications and research. In recent years, ontologies have regained interest also within the NLP community, specifically in such applications as information extraction, text mining and question answering. However, as ontology development is a tedious and costly process there has been an equally growing interest in the automatic learning of ontologies. Much of this work has been focused on textual data as human language is a primary mode of knowledge transfer. In this way, textual data provide both a resource for the ontology learning process as well as an application medium for developed ontologies.


Automatic methods for text-based ontology learning and population have developed over recent years, but it is difficult to compare approaches and results. In the 1st Workshop on Ontology Learning and Population (at ECAI 2004) we addressed this issue through an emphasis on the evaluation aspects of the reported work. In the context of the 2nd workshop we intend to continue this emphasis by providing a common data set for participants to work with, consisting of an ontology and document collection in the football (soccer) domain and a corresponding automatically extracted knowledge base. Participants will be free to use this or other data, but are encouraged to (also) use the OLP2 data set for their experiments in order to better compare results with other participants.

                                                                                                 
An additional topic we intend to address at this workshop is the relation between NLP and ontology development, the communities of which are working on similar topics but using different terminology. As this leads to a confound communication, the potential for interdisciplinary work becomes much less pronounced. We therefore intend the workshop to contribute to an enhanced interdisciplinary understanding of tasks, methods and evaluations.

 

Areas of Interest

 

To provide a clear focus we request novel work on:

- Concept formation on the basis of text

- Learning concept hierarchies / non-taxonomic relations / rules / axioms from text

- Named-Entity Recognition with respect to an ontology

- Ontology-based information extraction

- Ontology learning for IE, IR, MT, QA

- Gold standard and task-based evaluation of ontology learning, e.g. in IE, IR, MT, QA

 

Important Dates

 

April 20th

Submission Deadline

May 17th

Notification

June 2nd

Camera-ready Version

July 22nd

Workshop

 

Submission

 

Submissions should follow the two-column format of ACL proceedings and should not exceed eight (8) pages, including references. Submission will be electronic. The only accepted format for submitted papers is Adobe PDF. Papers must be submitted no later than April 20, 2006 (12 pm GMT) under:

 

http://www.softconf.com/acl/W5-COLINGACL2006/submit.html

 

Organizing Committee

 

Paul Buitelaar

DFKI, Germany

Philipp Cimiano

AIFB, Univ. of Karlsruhe, Germany

Berenike Loos

European Media Lab, Germany

 

Program Committee

 

Eneko Agirre

Basque Country University, Spain

Enrique Alfonseca

Universidad Autónoma de Madrid, Spain

Nathalie Aussenac-Gilles

IRIT- CNRS Toulouse, France

Timothy Baldwin

University of Melbourne, Australia

Roberto Basili

Universitŕ di Roma "Tor Vergata", Italy

Johan Bos

Universitŕ di Roma "La Sapienza", Italy

Christopher Brewster

University of Sheffield, UK

Massimiliano Ciaramita

LOA-ISTC, Italy

Nigel Collier

National Institute of Informatics, Japan

Ido Dagan

Bar Ilan University, Israel

Eric Gausier

XEROX XRCE, France

Asuncion Gomez-Perez

Universidad Politécnica de Madrid, Spain

Marko Grobelnik

Jožef Stefan Institute, Slovenia

Siegfried Handschuh

DERI Galway, Ireland

Andreas Hotho

University of Kassel, Germany

Eduard Hovy       

USC, Information Sciences Institute, USA

Vipul Kashyap

Partners HealthCare System, USA

Bernardo Magnini

ITC-IRST, Italy

Diana Maynard

University of Sheffield, UK

Adeline Nazarenko

LIPN - Université Paris-Nord, France

Claire Nedellec

MIG, INRA, France

George Paliouras

NCSR "Demokritos", Greece

Patrick Pantel

USC, Information Sciences Institute, USA

Robert Porzel

European Media Lab, Germany

Marie-Laure Reinberger

Universiteit Antwerpen, Belgium

Marta Sabou

Knowledge Media Institute, UK

Michael Sintek

DFKI, Germany

Peter Spyns

Vrije Universiteit Brussel, Belgium

Steffen Staab

University of Koblenz-Landau, Germany

Vojtech Svatek

University of Economics, Prague, Czech Rep.

Paola Velardi

Universitŕ di Roma "La Sapienza", Italy

Dominic Widdows

MAYA Design, USA

 

Workshop Registration

 

All workshop participants must register for COLING/ACL 2006

 

Links

 

Selected and extended papers from the ECAI 2004 Workshop on Ontology Learning and Population and the EKAW 2004 Workshop on the Application of Language and Semantic Technologies to Support Knowledge Management Processes have been published in:

 

Paul Buitelaar, Philipp Cimiano, Bernardo Magnini (eds.) Ontology Learning from Text: Methods, Evaluation and Applications Frontiers in Artificial Intelligence and Applications Series, Vol. 123, IOS Press, July 2005