Extending Ontologies for Annotating Business News Inna Novalija, Dunja Mladenić J. Stefan Institute, Slovenia 17 October, 2008.

Slides:



Advertisements
Similar presentations
A Semantic Web Approach to Digital Rights Management Roberto García González.
Advertisements

STRENGTHENING FINANCING FOR DEVELOPMENT: PROPOSALS FROM THE PRIVATE SECTOR Compiled by the UN-Sanctioned Business Interlocutors to the International Conference.
Opportunistic Reasoning for the Semantic Web: Adapting Reasoning to the Environment Carlos Pedrinaci Tim Smithers and Amaia Bernaras.
Ontology-based User Modeling for Web-based Information Systems Anton Andrejko, Michal Barla and Mária Bieliková {andrejko, barla,
Schema Matching and Query Rewriting in Ontology-based Data Integration Zdeňka Linková ICS AS CR Advisor: Július Štuller.
1 University of Namur, Belgium PReCISE Research Center Using context to improve data semantic mediation in web services composition Michaël Mrissa (spokesman)
Integrated Business Statistics Program (IBSP) Introduction Daniela Ravindra Director, Enterprise Statistics Division November 9th, 2010.
Using UML, Patterns, and Java Object-Oriented Software Engineering Chapter 1: Introduction.
Ontologies: Dynamic Networks of Formally Represented Meaning Dieter Fensel: Ontologies: Dynamic Networks of Formally Represented Meaning, 2001 SW Portal.
Copyright © 2002 Cycorp Introduction Fundamental Expression Types Top Level Collections Time and Dates Spatial Properties and Relations Event Types Information.
KEOD 2013 – 20 th September 2013 A Comprehensive Framework for Semantic Annotation of Web Content Manuel Fiorelli 1, Maria Teresa Pazienza 2, Armando Stellato.
Workpackage 2: Norms
UNCERTML - DESCRIBING AND COMMUNICATING UNCERTAINTY Matthew Williams
Xyleme A Dynamic Warehouse for XML Data of the Web.
Relational Data Mining in Finance Haonan Zhang CFWin /04/2003.
Knowledge Acquisitioning. Definition The transfer and transformation of potential problem solving expertise from some knowledge source to a program.
PDDL: A Language with a Purpose? Lee McCluskey Department of Computing and Mathematical Sciences, The University of Huddersfield.
Annotating Documents for the Semantic Web Using Data-Extraction Ontologies Dissertation Proposal Yihong Ding.
Knowledge Management Tools Abstract More and more companies use knowledge management to leverage theis most important resource : knowledge. Knowledge.
Information Modeling: The process and the required competencies of its participants Paul Frederiks Theo van der Weide.
11/8/20051 Ontology Translation on the Semantic Web D. Dou, D. McDermott, P. Qi Computer Science, Yale University Presented by Z. Chen CIS 607 SII, Week.
Ontology translation: two approaches Xiangkui Yao OntoMorph: A Translation System for Symbolic Knowledge By: Hans Chalupsky Ontology Translation on the.
B IOMEDICAL T EXT M INING AND ITS A PPLICATION IN C ANCER R ESEARCH Henry Ikediego
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
Knowledge Mediation in the WWW based on Labelled DAGs with Attached Constraints Jutta Eusterbrock WebTechnology GmbH.
Erasmus University Rotterdam Introduction With the vast amount of information available on the Web, there is an increasing need to structure Web data in.
ECTS definition : Student centred system, Student centred system, Based on student workload required to : Based on student workload required to : Achieve.
Blaz Fortuna, Marko Grobelnik, Dunja Mladenic Jozef Stefan Institute ONTOGEN SEMI-AUTOMATIC ONTOLOGY EDITOR.
An approach to Intelligent Information Fusion in Sensor Saturated Urban Environments Charalampos Doulaverakis Centre for Research and Technology Hellas.
Applying Belief Change to Ontology Evolution PhD Student Computer Science Department University of Crete Giorgos Flouris Research Assistant.
School of Computing FACULTY OF ENGINEERING Developing a methodology for building small scale domain ontologies: HISO case study Ilaria Corda PhD student.
Jessica Chen-Burger A Framework for Knowledge Sharing and Integrity Checking for Multi-Perspective Models Yun-Heh (Jessica) Chen-Burger Artificial Intelligence.
 Copyright 2008 Digital Enterprise Research Institute. All rights reserved. Semantic on the Social Semantic Desktop.
Ontology Evolution and Regression Analysis Insights into Ontology Regression Testing Maria Copeland Rafael Goncalvez Robert Stevens Bijan Parsia Uli Sattler.
An Ontological Framework for Web Service Processes By Claus Pahl and Ronan Barrett.
UNCERTML - DESCRIBING AND COMMUNICATING UNCERTAINTY WITHIN THE (SEMANTIC) WEB Matthew Williams
Knowledge Representation of Statistic Domain For CBR Application Supervisor : Dr. Aslina Saad Dr. Mashitoh Hashim PM Dr. Nor Hasbiah Ubaidullah.
2131 Structured System Analysis and Design By Germaine Cheung Hong Kong Computer Institute Lecture 8 (Chapter 7) MODELING SYSTEM REQUIREMENTS WITH USE.
 What is Modeling What is Modeling  Why do we Model Why do we Model  Models in OMT Models in OMT  Principles of Modeling Principles of Modeling 
Using Several Ontologies for Describing Audio-Visual Documents: A Case Study in the Medical Domain Sunday 29 th of May, 2005 Antoine Isaac 1 & Raphaël.
Andreas Abecker Knowledge Management Research Group From Hypermedia Information Retrieval to Knowledge Management in Enterprises Andreas Abecker, Michael.
Understanding User’s Query Intent with Wikipedia G 여 승 후.
Of 33 lecture 1: introduction. of 33 the semantic web vision today’s web (1) web content – for human consumption (no structural information) people search.
A View-based Methodology for Collaborative Ontology Engineering (VIMethCOE) Ernesto Jiménez Ruiz Rafael Berlanga Llavorí Temporal Knowledge Bases Group.
Volgograd State Technical University Applied Computational Linguistic Society Undergraduate and post-graduate scientific researches under the direction.
1 MedAT: Medical Resources Annotation Tool Monika Žáková *, Olga Štěpánková *, Taťána Maříková * Department of Cybernetics, CTU Prague Institute of Biology.
Revisions Proposed to the CIS Plan by the Global Office Misha V. Belkindas Budapest, July 3-4, 2013.
Finding frequent and interesting triples in text Janez Brank, Dunja Mladenić, Marko Grobelnik Jožef Stefan Institute, Ljubljana, Slovenia.
Application Ontology Manager for Hydra IST Ján Hreňo Martin Sarnovský Peter Kostelník TU Košice.
Semantic web Bootstrapping & Annotation Hassan Sayyadi Semantic web research laboratory Computer department Sharif university of.
Web Information Retrieval Prof. Alessandro Agostini 1 Context in Web Search Steve Lawrence Speaker: Antonella Delmestri IEEE Data Engineering Bulletin.
WSMO in Knowledge Web 2nd SDK cluster f2f meeting Rubén Lara Digital Enterprise.
Commonsense Reasoning in and over Natural Language Hugo Liu, Push Singh Media Laboratory of MIT The 8 th International Conference on Knowledge- Based Intelligent.
Personalized Recommendation of Related Content Based on Automatic Metadata Extraction Andreas Nauerz 1, Fedor Bakalov 2, Birgitta.
Approach to building ontologies A high-level view Chris Wroe.
Be.wi-ol.de User-friendly ontology design Nikolai Dahlem Universität Oldenburg.
Designing and Using an Audio-Visual Description Core Ontology Friday 8 th of October, 2004 Antoine Isaac & Raphaël Troncy.
Versatile Information Systems, Inc International Semantic Web Conference An Application of Semantic Web Technologies to Situation.
GoRelations: an Intuitive Query System for DBPedia Lushan Han and Tim Finin 15 November 2011
©2003 Paula Matuszek CSC 9010: AeroText, Ontologies, AeroDAML Dr. Paula Matuszek (610)
Lisbon, 30 th March 2016 Gianluca Luraschi Gonçalo Cadete “Towards a Methodology for Building.
FROM THE ESSENCE OF AN ENTERPRISE TOWARDS ENTERPRISE SUPPORTING INFORMATION SYSTEMS Tanja Poletaeva Tutors: Habib Abdulrab Eduard Babkin.
Business process management (BPM)
Business process management (BPM)
Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning Shizhu He, Cao liu, Kang Liu and Jun Zhao.
Survey of Knowledge Base Content
Methontology: From Ontological art to Ontological Engineering
Ontology-Based Approaches to Data Integration
Social Abstractions for Information agents
ONTOMERGE Ontology translations by merging ontologies Paper: Ontology Translation on the Semantic Web by Dejing Dou, Drew McDermott and Peishen Qi 2003.
Presentation transcript:

Extending Ontologies for Annotating Business News Inna Novalija, Dunja Mladenić J. Stefan Institute, Slovenia 17 October, 2008

O UTLINE Introduction Semantic technologies in the news domain Development of Financial Ontology Methodology Design criteria for ontology development Overview of the methodologies, Cyc method Preliminary experiments Financial news domain Discussion & Conclusion

I NTRODUCTION S EMANTIC TECHNOLOGIES IN THE NEWS DOMAIN Focus: manual extensions of ontologies to support the annotation of business news. Findings: proposed extensions of ontology results in annotation with better coverage of terms that are relevant for business domains. Why News? News reports are one of the largest sources of information about society. The analysis of news allows to make the important conclusions about trends in the society life. Semantic technologies already successfully applied for news analysis.

I NTRODUCTION R ESEARCH SCHEME Extending ontology Specific data Annotate news General knowledge News analysis

I NTRODUCTION S EMANTIC TECHNOLOGIES IN THE NEWS DOMAIN Challenges while using semantic technologies in news analysis: News are dynamic (constantly changing). News are interactive. News are socialy biased. News agencies produce huge amounts of content.

I NTRODUCTION D EVELOPMENT OF FINANCIAL ONTOLOGY Challenges while building Financial Ontology: Nature of the financial tasks dynamic, distributed, global, heterogeneous in nature large amount of continually changing, and generally unorganized, information available variety of all kinds of information (like market data, financial report data, breaking news, etc.) Slow standardization efforts high complexity of the financial standards high competition and dynamics of the financial sector influence the implementation of the new technologies Challenges for our work: Dynamics of the financial sector importance of the temporal aspects while building a Financial ontology Heterogeneity of financial information and tasks.

M ETHODOLOGY D ESIGN CRITERIA FOR ONTOLOGY DEVELOPING Design criteria for ontology development : Clarity, Coherence, Extendibility, Minimal encoding bias, Minimal ontological commitment. Additional methodological principles: Ontology double articulation, Ontology modularization principle. Our focus: clarity, extendibility and ontology modularization

M ETHODOLOGY O VERVIEW OF CANDIDATE METHODOLOGIES Ontology development methods/methodologies: Uschold and Kings method – methodology for ontology building, proposed in Grüninger and Foxs methodology – method based on competency questions, proposed in METHONTOLOGY - complete ontology development process; one of the most famous methodologies, proposed in On-To-Knowledge - developed in 2004 for introducing and maintaining ontology based knowledge management applications into enterprises. Cyc method - arises from the development of Cyc Knowledge Base, introduced in Our research: using Cyc method

M ETHODOLOGY C YC METHOD Phases of build the Cyc ontology: Manual encoding of the explicit and implicit knowledge appearing in the knowledge sources. Knowledge codification that is aided by tools using knowledge already stored in the Cyc KB. Delegating to the tools the majority of the work. Building top-down (first top level ontology containing the most abstracts concepts)

M ETHODOLOGY C YC KNOWLEDGE BASE One of the largest knowledge bases a formalized representation of a vast quantity of fundamental human knowledge: facts, rules of thumb, and heuristics for reasoning about the objects and events of everyday life Divided into the large number of microtheories, each of which represents the set of assumption for a particular knowledge domain Contains nearly concepts and several dozen hand- entered assertions about/involving each of them and different predicates. Assertions are continually added manually as well as automatically as a product of the inference process.

M ETHODOLOGY C YC Cyc gives an extremely powerful mechanism of creating and using different ontologies. Reasons for using Cyc in our research: Extensive amount of versatile integrated information Large number of assertions OpenCyc & ResearchCyc Flexible and convenient language (CycL) Suitable interface

P RELIMINARY EXPERIMENTS N EWS ANNOTATION - FINANCIAL NEWS DOMAIN Experiment: Random samples of ten news articles from two news datasets: Reuters and Yahoo Finance Manually annotated for financial terms (for evaluation) Cyc annotator applied on the news : using the original Cyc ontology simulating extension of the original Cyc ontology Reuters news: Set of 1450 news from1996 that were labeled as financial and business services I8 FINANCIAL AND BUSINESS SERVICES I81 BANKING AND FINANCIAL SERVICES I82 INSURANCE I831 FINANCIAL SERVICES I84 RENTING AND LEASING EQUIPMENT I85 REAL ESTATE DEALING Yahoo Finance news: News for the last three months (mid. May – mid. August 2008) news articles Uncategorized news materials with financial connotation

P RELIMINARY EXPERIMENTS O NTOLOGY EXTENSION BASED ON Y AHOO GLOSSARY OF FINANCIAL TERMS Manually identified Tagged by Cyc Recall: 63% compared to 41% Precision: 84% compared to 56%

P RELIMINARY EXPERIMENTS R ESULTS Results of the experiment: Annotating using the original Cyc Reuters news: precision 56% and recall 41% Yahoo financial news : precision 69% and recall 57% Publicly available Yahoo Financial Glossary Contains about 50% of the financial terms untagged or tagged incorrectly by Cyc (54% Reuters, 52% Yahoo financial news) Annotating simulating extension of Cyc by Yahoo Glossary increases the average precision and recall Reuters news: precision 84% and recall 63% Yahoo financial news : precision 82% and recall 73% Hypothesis to be tested in future work: Extension of Cyc ontology by the terms from Yahoo Financial Glossary improved annotation and analysis of the financial news

D ISCUSSION & C ONCLUSION Cyc gives powerful mechanisms for creation and extension of ontologies: Cyc knowledge base contains a large number of assertions Available for public/research: OpenCyc and ResearchCyc Flexible and convenient language (CycL) Suitable interface Financial Ontology developed within Cyc as basis for financial news analysis

Thank You for the Attention!