Ambiverse, a spin-off from the Max Planck Institute for Informatics, develops technologies to automatically understand, analyze, and manage Big Text collections. Ambiverse is built on years of state-of-the-art research in text analytics. In 2015, Ambiverse received an EXIST Transfer of Research grant by the German Federal Ministry for Economic Affairs and Energy.
Johannes has a keen interest in the big picture and making things work. He is the leading figure of Ambiverse, driving the vision of text to knowledge. Johannes did his PhD in artificial intelligence, specifically in natural language understanding, at the Max Planck Institute for Informatics.
Having a strong technical background in cloud solutions for natural language applications, Daniel leads our strategic engagement with customers and grows our market reach. Previously, he was in Globalization Services at SAP. He received a PhD in Computer Science from TU Darmstadt in 2013.
Dragan is a passionate coder with a knack for great visual design. With his background in knowledge-driven applications, he is driving all things engineering at Ambiverse. Dragan did his Masters in Computer Science at the Max Planck Institute for Informatics.
Luciano has the ability to solve language understanding problems in a principled but tractable manner, making him the key person for bringing research to applications. He completed a PhD in artificial intelligence, specifically natural language understanding, at the Max Planck Institute for Informatics.
Gerhard is a Research Director at the Max Planck Institute for Informatics. He supports Ambiverse with his extensive scientific expertise in natural language understanding, knowledge acquisition, and knowledge bases.
ClausIE: Clause-Based Open Information Extraction
Luciano Del Corro, Rainer Gemulla.
We propose ClausIE, a novel, clause-based approach to open information extraction, which extracts relations and their arguments from natural language text. ClausIE fundamentally differs from previous approaches in that it separates the detection of “useful” pieces of information expressed in a sentence from their representation in terms of extractions. ...
ClausIE solves open information extraction and is one of the most widely cited papers in the field
Luciano Del Corro, Rainer Gemulla. ClausIE: clause-based open information extraction. WWW 2013
Robust Disambiguation of Named Entities in Text
Johannes Hoffart, Mohamed Amir Yosef, Ilaria Bordino, Hagen Fürstenau, Manfred Pinkal, Marc Spaniol, Bilyana Taneva, Stefan Thater, Gerhard Weikum.
Disambiguating named entities in naturallanguage text maps mentions of ambiguous names onto canonical entities like people or places, registered in a knowledge base such as DBpedia or YAGO. This paper presents a robust method for collective disambiguation, by harnessing context from knowledge bases and using a new form of coherence graph. ...
One of the most widely cited entity linking papers and was referred to by IBM Watson as state-of-the-art
Johannes Hoffart, Mohamed Amir Yosef, Ilaria Bordino, Hagen Fürstenau, Manfred Pinkal, Marc Spaniol, Bilyana Taneva, Stefan Thater, Gerhard Weikum. Robust Disambiguation of Named Entities in Text. EMNLP 2011
YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia.
Johannes Hoffart, Fabian M. Suchanek, Klaus Berberich, Gerhard Weikum.
We present YAGO2, an extension of the YAGO knowledge base, in which entities, facts, and events are anchored in both time and space. YAGO2 is built automatically from Wikipedia, GeoNames, and WordNet. It contains 80 million facts about 9.8 million entities. Human evaluation confirmed an accuracy of 95% of the facts in YAGO2. ...
YAGO2 won the AI Journal Prominent Paper Award
Johannes Hoffart, Fabian M. Suchanek, Klaus Berberich, Gerhard Weikum. YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia. Artif. Intell. 194: 28-61 (2013)
- Gerhard Weikum and Johannes Hoffart and Fabian M. Suchanek. Ten Years of Knowledge Harvesting: Lessons and Challenges. IEEE Data Eng. Bull. 39(3): 41-50 (2016)
- Luciano Del Corro, Abdalghani Abujabal, Rainer Gemulla, Gerhard Weikum. FINET: Context-Aware Fine-Grained Named Entity Typing. EMNLP 2015
- Fabio Petroni, Luciano Del Corro, Rainer Gemulla. CORE: Context-Aware Open Relation Extraction with Factorization Machines. EMNLP 2015
- Luciano Del Corro, Rainer Gemulla, Gerhard Weikum. Werdy: Recognition and Disambiguation of Verbs and Verb Phrases with Syntactic and Semantic Pruning. EMNLP 2014
- Johannes Hoffart, Dragan Milchevski, Gerhard Weikum. STICS: searching with strings, things, and cats. SIGIR 2014.
- Johannes Hoffart, Yasemin Altun, Gerhard Weikum. Discovering emerging entities with ambiguous names. WWW 2014
- Johannes Hoffart, Stephan Seufert, Dat Ba Nguyen, Martin Theobald, Gerhard Weikum. KORE: keyphrase overlap relatedness for entity disambiguation. CIKM 2012
- Luciano Del Corro. Methods for open information extraction and sense disambiguation on natural language text. Saarland University 2016
- Johannes Hoffart. Discovering and disambiguating named entities in text. Saarland University 2015
- Daniel Bär. A composite model for computing similarity between texts. Doctoral Thesis. Darmstadt University of Technology 2013
- Dragan Milchevski. Entity Recommendation Based on Wikipedia. Saarland University 2013