Tools and Services

 

This is a list of tools and services being used in and further developed and tested in the LinkedTV project. Please note that all tools and services listed here should be considered experimental, research and possibly unstable. LinkedTV and the respective consortium partners accept no liability for the availability or correct functioning of these tools or services. If you interested in stable access to the functionalities enabled by any tool or service we suggest you to contact directly the responsible person.

Demo categories

LinkedTV platform

LinkedTV Platform

Description

The LinkedTV Platform is a RDF Repository (Triple/Quad Store) based on OpenLink Virtuoso for the permanent storage of all RDF data for annotated media fragments which are produced by the different LinkedTV components and services. Access to the RDF data is provided through a direct SPARQL endpoint as well as a custom REST API based on the Elda Linked Data API (http://code.google.com/p/elda/)

Download / API

http://data.linkedtv.eu/  (Web interface)
http://data.linkedtv.eu/sparql (SPARQL endpoint)
http://data.linkedtv.eu/fct/ (Faceted Search)

The API access and documentation are currently private.

Responsible partner

Condat

Contact person

Jan Thomsen


Linked media

NERD

Description

A Framework compiling 10 NER extractors including: AlchemyAPI, DBpedia Spotlight, Extractiv, Lupedia, OpenCalais, Saplo, SemiTags, Wikimeta, Yahoo! Content Analysis Framework and Zemanta (Evri is no longer available). NERD detects automatically the language of the text being analyzed. NERD provides an individual dashboard to monitor logged in user activity.

Download / API

http://nerd.eurecom.fr/api/

Endpoint Documentation

http://nerd.eurecom.fr/documentation

Presentation / tutorial

http://www.slideshare.net/giusepperizzo/nerd-11974343

Responsible partner

EURECOM

Contact

Retrieve contact


SemiTags

Description

It is a Named Entity Recognition and Disambiguation Web Service

Download / API

http://ner.vse.cz/SemiTags/rest/v1/recognize

Endpoint Documentation

http://ner.vse.cz/SemiTags/app/static/developers

Responsible partner

University of Economics, Prague

Contact person

Ivo Lašek


THD

Description

THD is advanced hypernym discovery tool. Its goal is not to find all hypernyms in the corpus but rather to find hypernyms for a specific entity. THD also has the advantage of requiring no training and uses up-to-date on-line resources to find hypernyms in real time.

Download / API

http://entityclassifier.eu/thd/api/v1/extraction

Endpoint Documentation

http://www.entityclassifier.eu/thd/docs/

Responsible partner

University of Economics, Prague

Contact person

Tomas Kliegr


Linked Hypernyms Dataset

Description

This Linked Hypernym dataset attaches entity articles in English, German and Dutch Wikipedia with a DBpedia resource or a DBpedia ontology concept as their type. The types are hypernyms mined from articles’ free text using hand-crafted lexicosyntactic patterns. The dataset contains 2.8 million entity-type assignments, out of which nearly 2.5 million are novel with respect to DBpedia and 2 million w.r.t. Yago 2s and DBpedia.

Download / API

http://ner.vse.cz/datasets/linkedhypernyms/

Documentation

http://ner.vse.cz/datasets/linkedhypernyms/dataset-description/

Responsible partner

University of Economics, Prague

Contact person

Tomas Kliegr

 


Wikifier Evaluation Framework for GATE

Description

GATE plugins for evaluation of Wikipedia-based NER systems (also known as Wikifiers), which provide links to Wikipedia articles describing recognized entities, and classify those entities with types from the DBpedia Ontology. The plugins come with two evaluation datasets. The News dataset – consists of a small number of standard-length news articles freely available from the BBC and New York Times. The dataset is a derivative of the originally published WEKEX dataset. This dataset is released under the Creative Commons BY-SA 3.0 license.

Download / API

http://ner.vse.cz/datasets/evaluation/

Documentation

http://ner.vse.cz/datasets/evaluation/tools/

Responsible partner

University of Economics, Prague

Contact person

Milan Dojchinovski


Linked Services Infrastructure (LSI)

Description

The REST API of the Linked Services Infrastructure provides a programmatic means to integrate LSI functionality into other tools and services. The LSI takes a Linked Data URI and returns a set of relevant media resources from the open Web.

Endpoint

http://production.sti2.org/lsi/api/invoke

Endpoint Documentation

http://production.sti2.org/lsi/docs/index.html

Responsible partner

STI International

Contact person

Lyndon Nixon


Personalisation

EasyMiner

Description

Easy Miner is a web interface to the association rule mining system LISp-Miner. Its user interface resembles a web search engine. Easy Miner discovers multi-valued attributes, supports full range of logical connectives and 19 interest measures. An experimental relevance feedback module is used to filter rules based on previous user interactions.

Download / API

http://sewebar-demo.lmcloud.vse.cz/izi-miner/

Endpoint Documentation

http://easyminer.eu/

Presentation / tutorial

http://easyminer.eu/feature-tutorial 

Responsible partner

University of Economics, Prague

Contact person

Tomas Kliegr


GAIN

Description

Framework for capturing and preprocessing user interaction and implicit feedback

Endpoint

API access is not yet public

Endpoint Documentation

http://inbeat.eu/gain/docs/

Responsible partner

University of Economics, Prague

Contact person

Tomas Kliegr


LinkedTV User Model Editor (LUME)

Description

The User Model Editor provides a RESTful API for further integration with other LinkedTV components, in particular with the LinkedTV video player.

Endpoint

http://data.linkedtv.eu:8081/LUME3-war/service

Responsible partner

Fraunhofer IAIS

Contact person

Rüdiger Klein


LinkedTV Semantic Filtering (LSF)

Description

The LinkedTV Semantic Filter provides a RESTful API for further integration with other LinkedTV components, in particular with the LinkedTV video player.

Endpoint

http://data.linkedtv.eu:8081/LUME3-war/service

Responsible partner

Fraunhofer IAIS

Contact person

Rüdiger Klein


LinkedTV User Model Ontology (LUMO)

Description

The LUMO ontology is developed within the LinkedTV project to semantically represent user-pertinent information, in order to enable semantic personalization and contextualization (i.e. filtering) of concepts and content in the networked media domain. LUMO is currently accompanied by a separate mappings ontology, modelling mappings of LUMO to several existing ontologies and vocabularies.

Homepage

http://mklab.iti.gr/project/lumo

Download / API

LUMO: http://data.linkedtv.eu/ontologies/lumo
LUMO mappings: http://data.linkedtv.eu/ontologies/lumo_mappings/

Endpoint Documentation

LUMO: http://data.linkedtv.eu/ontologies/lumo/lumo_doc/index.html
LUMO mappings: http://data.linkedtv.eu/ontologies/lumo_mappings/lumo_mappings_doc/index.html

Responsible partner

CERTH-ITI

Contact person

Dorothea Tsatsou
Vasileios Mezaris


f-PocketKRHyper

Description

f-PocketKRHyper is a general purpose fuzzy semantic reasoner, which for the purposes of LinkedTV performs content filtering by semantically matching a user profile against a set of available content items, and concept filtering by expanding the interests of a user along the LinkedTV personalization concept space (LUMO).

Download / API

http://mklab.iti.gr/project/f-pocketkrhyper

Endpoint Documentation

http://mklab.iti.gr/project/f-pocketkrhyper

Responsible partner

CERTH-ITI

Contact person

Dorothea Tsatsou
Vasileios Mezaris


Linked Profiler

Description

Linked Profiler is a semantic profile engineering API, responsible for receiving input by captured or explicitly declared user interests and (a) unifying it under a common personalisation-centric vocabulary LUMO and, based on the uniform input (b) learning a user profile over time and content consumption through its subcomponent Simple Learner. It ultimately produces a fuzzy semantic user profile that can be received by the LinkedTV filtering tools.

Download / API

http://mklab.iti.gr/project/linkedtv-profiling-tools

Endpoint Documentation

http://mklab.iti.gr/project/linkedtv-profiling-tools

Responsible partner

CERTH-ITI

Contact person

Dorothea Tsatsou
Vasileios Mezaris


Media analysis

Mixture Subclass Discriminant Analysis (MSDA)

Description

MSDA is a supervised dimensionality reduction technique that overcomes the nonlinearity problem of LDA by deriving a subclass data division and the respective lower dimensional subspace suitable for sample discrimination. In the particular implementation the negentopy increment is used to implement a nongaussianity criterion for deriving the best subclass partition. Moreover, the nearest neighbor method is used in the derived subspace for classifying unlabeled observations. This method is generic and can be used in a very wide range of learning problems; in LinkedTV, it is used primarily as part of our solutions to the event detection problem.

Download / API

http://www.iti.gr/~bmezaris/downloads.html

Endpoint Documentation

http://www.iti.gr/~bmezaris/downloads.html

Responsible partner

CERTH-ITI

Contact person

Nikolaos Gkalelis
Vasileios Mezaris


Keyword Extraction Tool

Description

Keyword extraction is a Web application and Web service, which performs keyword extraction from English, German and Dutch text. The system is based on the standard TF-IDF approach, which is extended with language-specific POS tagging and noun-phrase chunking for identification of key phrases.

Download / API

https://ner.vse.cz/KeywordExtraction/rest/v2 

Endpoint Documentation

https://ner.vse.cz/KeywordExtraction/developers.html

Responsible partner

UEP

Contact person

Tomas Kliegr

Leave a Comment

You must be logged in to post a comment.