rapid prototyping of a semantic-web-based research workbench

16
Rapid Prototyping of a Semantic-Web-based Research Workbench Carsten Ullrich Dept. of Computer Science and Engineering, SJTU

Upload: carsten-ullrich

Post on 27-Jan-2015

103 views

Category:

Technology


0 download

DESCRIPTION

Talk at the UDS-SJTU Joint Research Lab for Language Technology.I describe I project I did for Totuba.

TRANSCRIPT

Page 1: Rapid Prototyping of a Semantic-Web-based Research Workbench

Rapid Prototyping of a Semantic-Web-based Research Workbench

Carsten Ullrich

Dept. of Computer Science and Engineering, SJTU

Page 2: Rapid Prototyping of a Semantic-Web-based Research Workbench

Overview

• Project done with Totuba, Inc.

• Goal: develop a research workbench– bibliography manager– research network– support while writing research papers

• Sorry, no new pure research results

• But: overview on state-of-the-art of existing Web services / Web data

Page 3: Rapid Prototyping of a Semantic-Web-based Research Workbench

• context-sensitive further reading

• related topics

• drag&drop referencing

Page 4: Rapid Prototyping of a Semantic-Web-based Research Workbench

Entity Extraction

The term "Web 2.0" is used to describe applications that distinguish themselves from previous generations of software by a number of principles. Existing work shows that Web 2.0 applications can be successfully exploited for technology-enhanced learning. However, in-depth analyses of the relationship between Web 2.0 technology on the one hand and teaching and learning on the other hand are still rare.

Page 5: Rapid Prototyping of a Semantic-Web-based Research Workbench

Entity Extraction

Gur grez "Jro 2.0" vf hfrq gb qrfpevor nccyvpngvbaf gung qvfgvathvfu gurzfryirf sebz cerivbhf trarengvbaf bs fbsgjner ol n ahzore bs cevapvcyrf. Rkvfgvat jbex fubjf gung Jro 2.0 nccyvpngvbaf pna or fhpprffshyyl rkcybvgrq sbe grpuabybtl-raunaprq yrneavat. Ubjrire, va-qrcgu nanylfrf bs gur eryngvbafuvc orgjrra Jro 2.0 grpuabybtl ba gur bar unaq naq grnpuvat naq yrneavat ba gur bgure unaq ner fgvyy ener.

Page 6: Rapid Prototyping of a Semantic-Web-based Research Workbench

Entity Extraction

Gur grez "Jro 2.0" vf hfrq gb qrfpevor nccyvpngvbaf gung qvfgvathvfu gurzfryirf sebz cerivbhf trarengvbaf bs fbsgjner ol n ahzore bs cevapvcyrf. Rkvfgvat jbex fubjf gung Jro 2.0 nccyvpngvbaf pna or fhpprffshyyl rkcybvgrq sbe grpuabybtl-raunaprq yrneavat. Ubjrire, va-qrcgu nanylfrf bs gur eryngvbafuvc orgjrra Jro 2.0 grpuabybtl ba gur bar unaq naq grnpuvat naq yrneavat ba gur bgure unaq ner fgvyy ener.

OpenCalais

• Jro 2.0• grpuabybtl-raunaprq yrneavat

Page 7: Rapid Prototyping of a Semantic-Web-based Research Workbench

Open Calais

• Thomson Reuters company

• Web Service

• Extracts entities, facts, events (about 100 types)

• Free for noncommercial and commercial use

EntitiesAnniversary, City, Company, Continent, Country, Currency, EmailAddress, EntertainmentAwardEvent, Facility, FaxNumber, Holiday, IndustryTerm, MarketIndex, MedicalCondition, MedicalTreatment, Movie, MusicAlbum, MusicGroup, NaturalFeature, OperatingSystem, Organization, Person, PhoneNumber, Position, Product, ProgrammingLanguage, ProvinceOrState, PublishedMedium, RadioProgram, RadioStation, Region, SportsEvent, SportsGame, SportsLeague, Technology, TVShow, TVStation, URL

Page 8: Rapid Prototyping of a Semantic-Web-based Research Workbench

Semantifying

The term "Web 2.0“...

OpenCalais

• Web 2.0• technology-supported learning

DBPedia (others: Yago, Freebase, UMBEL)

• http://dbpedia.org/resource/Web_2.0• http://dbpedia.org/resource/Technology-Enhanced_Learning

Page 9: Rapid Prototyping of a Semantic-Web-based Research Workbench

Related Topics: Web_2.0 in DBPedia

• skos:subject – dbpedia:Category:Buzzwords– dbpedia:Category:Branding– dbpedia:Category:Cloud_applications– dbpedia:Category:Internet_memes– dbpedia:Category:Social_Information_Proces

sing– dbpedia:Category:World_Wide_Web– dbpedia:Category:Web_2.0– dbpedia:Category:Web_services

Page 10: Rapid Prototyping of a Semantic-Web-based Research Workbench

Linked Open Data dataset cloud

Page 11: Rapid Prototyping of a Semantic-Web-based Research Workbench

Reuse

• Highly efficient entity extraction• Enormous databases

– describe the entities– link to related entities

• Give a high-level starting position to explore new challenges– how to put this data into use?– context: what is relevant for user/current usage

Page 12: Rapid Prototyping of a Semantic-Web-based Research Workbench

Lessons Learned

• Reuse enables progress– no duplication of work– focus on problems relevant for you

• Having a landscape that encourages reuse creates advantages for research / commercial applications

• Problems– mostly only English– few Chinese services / programming libraries

• e.g., named entity extraction

Page 13: Rapid Prototyping of a Semantic-Web-based Research Workbench

Questions

• I have some:– opinion mining – information extraction

Page 14: Rapid Prototyping of a Semantic-Web-based Research Workbench
Page 15: Rapid Prototyping of a Semantic-Web-based Research Workbench
Page 16: Rapid Prototyping of a Semantic-Web-based Research Workbench

Questions

• I have some:– opinion mining – information extraction

• Any toolkits available? RASCALLI?

• Contact me in case you find this interesting

[email protected]