LIMES: LInk discovery framework for MEtric Spaces

  • screenshot

LIMES is a link discovery framework for the Web of Data. It implements time-efficient approaches for large-scale link discovery based on the characteristics of metric spaces. It is easily configurable via a web interface. It can also be downloaded as standalone tool for carrying out link discovery locally.

Demo Issues Download

General Overview

LIMES implements novel time-efficient approaches for link discovery in metric spaces. Our approaches different approximation techniques to compute estimates of the similarity between instances. These estimates are then used to filter out a large amount of those instance pairs that do not suffice the mapping conditions. By these means, LIMES can reduce the number of comparisons needed during the mapping process by several orders of magnitude. The approaches implemented in LIMES include the original LIMES algorithm for edit distances, REEDED for weighted edit distances, HR3, HYPPO, and ORCHID. Moreover, LIMES implements supervised and unsupervised machine-learning algorithms for finding accurate link specifications. The algorithms implemented here include the supervised, active and unsupervised versions of EAGLE, COALA and EUCLID.


The LIMES framework consists of seven main modules of which each can be extended to accommodate new or improved functionality. The central modules of LIMES are the controller module, which coordinates the matching process and the data module, which contains all the classes necessary to store data. The matching process is carried out as follows: First, the controller calls the I/O-module, which reads the configuration file and extracts all the information necessary to carry out the comparison of instances, including the URL of the SPARQL-endpoints of the knowledge bases, the restrictions on the instances to map (e.g., their type), the expression of the metric to be used and the threshold to be used. Examples of configuration files can be found in the distribution.

Given that the configuration file is valid w.r.t. the LIMES Specification Language (LSL), the query module is called. This module uses the configuration for the target and source knowledge bases to retrieve instances and properties from the SPARQL-endpoints of the source and target knowledge bases that adhere to the restrictions specified in the configuration file. The query module writes its output into a cache, which can be a file (for large number of instances, not implemented yet) or main memory. Once all instances have been stored in the cache, the controller calls the LIMES engine which runs through the specification and computes the results. The results are finally returned as RDF or TSV files.

Evaluation Results

The algorithms implemented in LIMES were published in several papers. Below are links to evaluation results.

Running LIMES

Running LIMES can be carried in one of three ways.

Current Team


by (Editors: ) [BibTex of ]


Additional contributions to SEMANTiCS 2014 ( 2014-08-05T10:31:12+02:00 RicardoUsbeck)

2014-08-05T10:31:12+02:00 RicardoUsbeck

Hello again! Unfortunately, we missed the opportunity to inform you about other contributions of AKSW to the SEMANTiCS 2014. First, we missed to tell you about another accepted paper: Towards Question Answering on Statistical Linked Data ( Konrad Höffner and Jens Lehmann) Second, there is also another excellent and interesting series of workshops. Read more about "Additional contributions to SEMANTiCS 2014"

Five AKSW Papers at SEMANTiCS 2014 ( 2014-08-01T16:54:00+02:00 RicardoUsbeck)

2014-08-01T16:54:00+02:00 RicardoUsbeck

Hello Community! We are very pleased to announce that five of our papers were accepted for presentation at SEMANTiCS 2014.  The papers cover architectures for Big Data Search Engines, Linked Data Visualisations, Machine Learning and Dataset Descriptions. Read more about "Five AKSW Papers at SEMANTiCS 2014"

Five AKSW Papers at ESWC 2014 ( 2014-03-14T01:37:52+01:00 by Dr. Axel-C. Ngonga Ngomo)

2014-03-14T01:37:52+01:00 by Dr. Axel-C. Ngonga Ngomo

Hello World! We are very pleased to announce that five of our papers were accepted for presentation at ESWC 2014. These papers range from natural-language processing to the acquisition of temporal data. Read more about "Five AKSW Papers at ESWC 2014"

Two AKSW Papers at ESWC ( 2013-02-25T17:28:02+01:00 by Dr. Axel-C. Ngonga Ngomo)

2013-02-25T17:28:02+01:00 by Dr. Axel-C. Ngonga Ngomo

Greetings World. We are happy to announce that the AKSW papers “COALA – Correlation-Aware Active Learning of Link Specifications” and “When to Reach for the Cloud: Using Parallel Hardware for Link Discovery” were selected for presentation at ESWC 2013. Each of the papers deals with one of the two main hurdles to scalable Link Discovery. Read more about "Two AKSW Papers at ESWC"

More than 20 European Union Datasets Converted to RDF by LATC Project ( 2012-07-09T15:13:52+02:00 by Dr. Jens Lehmann)

2012-07-09T15:13:52+02:00 by Dr. Jens Lehmann

Over the past two years, the LATC project (Linked Open Data Around-The-Clock) has worked on converting more than 20 EU datasets to RDF, make them available as Linked Data and SPARQL, and link them to other datasets. The datasets have gone through internal quality assurance against a publication checklist. Read more about "More than 20 European Union Datasets Converted to RDF by LATC Project"