Project

DEEPLEE

Tiefes Lernen für End-to-End-Anwendungen in der Sprachtechnologie

Tiefes Lernen für End-to-End-Anwendungen in der Sprachtechnologie

  • Duration:

The research work in DEEPLEE, which is carried out in the Language Technology research departments in Saabrücken and Berlin, builds on DFKI's expertise in the areas of "deep learning" (DL) and "language technology" (LT) and develops it further. They aim for profound improvements of DL approaches in LT by focusing on four central, open research topics:

  1. Modularity in DNN architectures
  2. Use of external knowledge
  3. DNNs with explanation functionality
  4. Machine Teaching Strategies for DNNs

The result of the research work will be a DL-based modular framework system that enables end-to-end applications in information extraction (IE), question answering (QA) and machine translation (MT). The following research objectives are pursued:

  1. Complex LTs (IE, QA, MT), which are traditionally based on heterogeneous technology collections, are to be modeled as uniform end-to-end learning scenarios based on neural networks.
  2. The end-to-end performance of classical approaches based on heterogeneous technology collections is to be evaluated against neural approaches.
  3. A repertoire of "linguistically inspired" neural building blocks for LTs will be established, which are linguistically-agnostic and can be reused (including explanatory functionality and learning aspects such as different degrees of monitoring, model distribution, transfer learning, multi-task learning for such modules). We will do this for IE, QA and MT scenarios covering a wide range of building blocks and applications.
  4. A portfolio of approaches to a variety of DNNs and tasks (NMT, NQA and NIE) will be established, which can be explained to a human expert.
  5. IE, QA and MT are to be designed as text-to-text applications.
  6. Development and evaluation of ways to integrate external knowledge sources into NN-based LTs.

Publications about the project

Sudip Kumar Naskar, Nico Herbig, Antonio Krüger, Josef van Genabith

In: Proceedings of the 28th Conference on Computational Linguistics. International Conference on Computational Linguistics (COLING-2020) December 12-13 Barcelona Spain Pages 5963-5974 International Committee on Computational Linguistics 12/2020.

To the publication
Necip Oğuz Şerbetci, Nils Rethmeier, Sebastian Möller, Roland Roller

In: AMIA 2020 ANNUAL SYMPOSIUM. AMIA Annual Symposium (AMIA-2020) November 14-18 Virtual PubMed 11/2020.

To the publication
Tim Schlippe, Thomas Mandl, Daniel Schiffner, Thierry Declerck,

In: Stefan Conrad , Ilaria Tiddi (editor). Proceedings of the CIKM 2020 Workshops,. International Workshop on Investigating Learning During Web Search (IWILDS-2020) located at CIKM 2020 October 19-19 Galway Ireland CEUR Workshop Proceedings 10/2020.

To the publication

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz