GERBIL: General Entity Annotation Benchmark Framework

GERBIL is a general entity annotation system based on the BAT-Framework.

Source Code Demo Issues Wiki

Overview of GERBIL
The need to bridge between the unstructured data on the document Web and the structured data on the Data Web has led to the development of a considerable number of annotation tools. Those tools are hard to compare since published results are calculated on diverse datasets and measured in different units. A first approach to structure the parameter- and tool-space of semantic entity annotation systems was published by Cornolti et al.. However, the BAT-framework is hard to setup and does not allow for an easy comparison of tools and datasets.

We present GERBIL, a general entity annotation system based on the BAT-Framework. GERBIL offers an easy-to-use web-based platform for the agile comparison of annotators using multiple datasets and uniform measuring approaches. To add a tool to GERBIL, all the end user has to do is to provide a URL to a REST interface to its tool which abides by a given specification. The integration and benchmarking of the tool against user-specified datasets is then carried out automatically by the GERBIL platform. Currently, our platform provides results for 9 annotators and 11 datasets with more coming. Internally, GERBIL is based on the Natural Language Programming Interchange Format (NIF) and provide Java classes for implementing APIs for datasets and annotators to NIF.

Annotators BAT-Framework Gerbil 1.0.0 Gerbil 1.2.2
Wikipedia Miner
Illionois Wikifier
Spotlight
TagMe 2
KEA
WAT
AGDISTIS (✔)
Babelfy
NERD-ML
NIF-based Annotator
AIDA
entityclassifier.eu (✔)
FREME e-Entity
CETUS
FRED
A2KB, C2KB, D2KB,
Entity Recognition
Entity Typing OKE Task 1 OKE Task 2
AIDA/CoNLL-Complete
AIDA/CoNLL-Test A
AIDA/CoNLL-Test B
AIDA/CoNLL-Training
AQUAINT
DBpediaSpotlight
IITB
KORE50
MSNBC
Microposts 2014-Test
Microposts 2014-Train
N3-RSS-500
N3-Reuters-128
OKE 2015 Task 1 evaluation dataset
OKE 2015 Task 1 example set
OKE 2015 Task 1 gold standard sample
OKE 2015 Task 2 evaluation dataset
OKE 2015 Task 2 example set
OKE 2015 Task 2 gold standard sample

Long term stability

The idea of GERBIL emerged in September 2014 when a couple of articles released at the same time claimed to be state-of-the-art. Especially, those approaches were not easily comparable due to their heterogeneous set-up, dataset use and evaluation metrics. Thus, we decided to build GERBIL and extend the BAT-Framework to break the barriers for people not able to write source code. GERBIL is still a young project and thus we are trying to explore the borders of our endeavour. As GERBIL has been launched within two PhD projects funded by European Social Fund we are confident that it will be a long lasting web service. The fallback is our working group AKSW which currently already hosts more than 30 open source projects. Finally, GERBIL is open source software which can be maintained and hosted by anybody.

Furthermore, the research and developement unit of the University Leipzig Computation Center keeps daily backups to ensure long-term quotability.

With this project we aim at establishing a highly available, easy quotable and liable focal point for NER and NED evaluations. Additionally, we build our framework to be rapidly extensible and adaptable for future uses.

The survey data from our paper can be found at GERBIL's GitHub repository.

Contributors

  • Ciro Baron (University Leipzig, Germany)
  • Andreas Both (R&D, Unister GmbH, Germany)
  • Martin Brümmer (University Leipzig, Germany)
  • Diego Ceccarelli (Unversity Pisa, Italy)
  • Marco Cornolti (University of Pisa, Italy)
  • Didier Cherix (R&D, Unister GmbH, Germany)
  • Bernd Eickmann (R&D, Unister GmbH, Germany)
  • Paolo Ferragina (University of Pisa, Italy)
  • Christiane Lemke (R&D, Unister GmbH, Germany)
  • Andrea Moro (Sapienza University of Rome, Italy)
  • Roberto Navigli (Sapienza University of Rome, Italy)
  • Francesco Piccinno (University of Pisa, Italy)
  • Giuseppe Rizzo (EURECOM, France)
  • Harald Sack (HPI Potsdam, Germany)
  • René Speck (Institute for Applied Informatics, Germany)
  • Raphaël Troncy (EURECOM, France)
  • Jörg Waitelonis (HPI Potsdam, Germany)
  • Lars Wesemann (R&D, Unister GmbH, Germany)

Project Team

Publications

by (Editors: ) [BibTex of ]

News

AKSW Colloquium, 23.05.2016, Instance Matching and RDF Dataset Similarity ( 2016-05-23T14:24:06+02:00 Michael Roeder)

2016-05-23T14:24:06+02:00 Michael Roeder

In the incoming colloquium, Mofeed Hassan will present the paper “Semi-supervised Instance Matching Using Boosted Classifiers” from Kejriwal et al., published in the proceedings of ESWC 2015 [PDF]. Read more about "AKSW Colloquium, 23.05.2016, Instance Matching and RDF Dataset Similarity"

AKSW Colloquium, 09.05.2016: Hebrew MMoOn inventory, federated SPARQL query processing ( 2016-05-03T13:57:03+02:00 by Bettina Klimek)

2016-05-03T13:57:03+02:00 by Bettina Klimek

In this week’s colloquium Bettina Klimek will give a practice talk of the paper ‘Creating Linked Data Morphological Language Resources with MMoOn – The Hebrew Morpheme Inventory‘, which she will present at the LREC conference 2016, 23-28 May 2016, Slovenia, … Continue reading → Read more about "AKSW Colloquium, 09.05.2016: Hebrew MMoOn inventory, federated SPARQL query processing"

AKSW Colloquium, 25.04.2016, DISPONTE, Workbench for Big Data Dev ( 2016-04-22T16:05:08+02:00 by Mohamed Sherif)

2016-04-22T16:05:08+02:00 by Mohamed Sherif

In this colloquium, Frank Nietzsche will present his master thesis titled “Game Theory- distributed solving” Game theory analyzes the behavior of individuals in complex situations. One popular game in Europe and North America with such a complex situation is Skat. Read more about "AKSW Colloquium, 25.04.2016, DISPONTE, Workbench for Big Data Dev"

AKSW Colloquium, 18.04.2016, DISPONTE, Workbench for Big Data Dev ( 2016-04-18T10:17:10+02:00 by Patrick Westphal)

2016-04-18T10:17:10+02:00 by Patrick Westphal

In this week’s Colloquium, today 18th of April at 3 PM, Patrick Westphal will present the paper ‘Probabilistic Description Logics under the Distribution Semantics‘ by Riguzzi et. al. Abstract Representing uncertain information is crucial for modeling real world domains. Read more about "AKSW Colloquium, 18.04.2016, DISPONTE, Workbench for Big Data Dev"

AKSW Colloquium, 11.04.2016, METEOR with DBnary ( 2016-04-11T09:07:18+02:00 by Ricardo Usbeck)

2016-04-11T09:07:18+02:00 by Ricardo Usbeck

In this week’s Colloquium, today 11th of April at 3 PM, Diego Moussallem will present the paper by Zied Elloumi et al. titled “METEOR for Multiple Target Languages using DBnary.” [PDF]. Read more about "AKSW Colloquium, 11.04.2016, METEOR with DBnary"