AmbiverseNLU: Open Source natural language understanding suite now available

We are happy to announce the open source release of the Ambiverse Natural Language Understanding suite (AmbiverseNLU)

developed at the Max Planck Institute for Informatics and Ambiverse GmbH.

AmbiverseNLU comprises knowledge-driven Named Entity Recognition, Entity & Concept Linking, Open Information Extraction, Entity Salience, and Knowledge Graph access components in many languages (English, Chinese, Czech, German, Spanish, Russian, within an extensible framework), providing a basis for text-to-knowledge applications. The components are based on robust and well-tested methods (AIDA [1], ClausIE [2], KnowNER [3]). The code is available under the Apache 2.0 licence on GitHub: .

Try the demo ( or sign up to the AmbiverseNLU mailing list (

We are looking forward to your feedback and questions!

The Ambinauts

[1] J. Hoffart, M. A. Yosef, I. Bordino, H. Fürstenau, M. Pinkal, M. Spaniol, B. Taneva, S. Thater, and G. Weikum, “Robust Disambiguation of Named Entities in Text,” Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, EMNLP 2011, Edinburgh, Scotland, 2011.
[2] L. Del Corro and R. Gemulla, “ClausIE - clause-based open information extraction.,” Proceedings of the 22nd International Conference on World Wide Web, WWW 2013, Rio de Janerio, Brazil, 2013.
[3] D. Seyler, T. Dembelova, L. Del Corro, J. Hoffart, and G. Weikum, “A Study of the Importance of External Knowledge in the Named Entity Recognition Task,” 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 2018.

Received on Thursday, 6 December 2018 14:29:04 UTC