Skip to main content Skip to main navigation
MLT Headerbild© Adobe Stock

Multilinguality and Language Technology

QAIE Team

We are a team at the MLT-Lab at DFKI specializing on Question Answering (QA) and Information Extraction (IE) – simply QAIE.

Question Answering and Information Extraction are closely related sharing many methodologies and sub-tasks. We research and develop methods combining Language Technology, Machine Learning and Deep Learning from core components to complete end-to-end solutions. We develop QAIE solutions in many application areas, including e-Health, BioNLP, e-Learning, and intelligent assistance.

Demo: Automatic Question Generation with Deep Learning

Some current projects:

AI4KOnCO

The major goal of the AI4KOnCO project is to provide parents and patients with the necessary support to confidently and knowledgeably consent to recommended treatment options. The project is funded through HEALTH.AI.

Project Page

HEGEMON

The goal of the HEGEMON project (funded by  cyperagentur)  is to competitively develop domain-specific benchmark sets — comprising tasks, metrics, and test datasets — alongside tailored AI models for defined use cases, enabling a thorough evaluation of pre-trained generative AI base models, such as text-image models.

 Project Page

AtLaS

The EU-funded AtLaS project, focused on advancing Human Language Technology (HLT), combines artificial intelligence (AI) and Natural Language Processing (NLP) to handle low-quality and multilingual data.

Project Page

PERKS

Eliciting and Exploiting Procedural Knowledge in Industry 5.0.

The EU-funded PERKS project supports the holistic governance of industrial PK Procedural Knowledge in its entire life cycle, from elicitation to management and from access to exploitation. 

Project Page

Meere Online

Meere Online is a project of the German Marine Research Alliance in the core area of transfer. Scientific facts on relevant marine topics are compiled on the digital information portal Meere Online. As a highlight, an AI-supported search will make it easier for users to access the topics.

Project Page

Selected recent publications:

  • Julian Schlenker, Jenny Kunz, Tatiana Anikina, Günter Neumann, and Simon Ostermann (2025) Only for the Unseen Languages, Say the Llamas: On the Efficacy of Language Adapters for Cross-lingual Transfer in English-centric LLMs, Proceedings of the 63st Annual Meeting of the Association for Computational Linguistics (Student Research Workshop). ACL Student Research Workshop (ACL-IJCNLP-SRW-2025), located at ACL (ACL-IJCNLP-SRW-2025), Italy, 2025.
  • Muhammad Umer Tariq Butt; Stalin Varanasi, and Günter Neumann (2025) Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO, Proceedings of 47th European Conference on Information Retrieval (ECIR 2025), Italy, 2025.
  • Noon Pokaratsiri, Saadullah Amin, and Günter Neumann (2024) Towards Understanding Attention-based Reasoning through Graph Structures in Medical Codes Classification, Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing at ACL-2024 (TextGraphs 2024), Bangkok, Thailand, 2024.
  • Stalin Varanasi, Muhammad Umer Butt, and Günter Neumann (2023) AutoQIR: Auto-Encoding Questions with Retrieval Augmented Decoding for Unsupervised Passage Retrieval and Zero-shot Question Generation, Proceedings of Recent Advances in Natural Language Processing (RANLP-2023), Bulgaria, 2023.
  • Saadullah Amin, Pasquale Minervini, David Chang, Pontus Stenetorp, and Günter Neumann (2022) MedDistant19: Towards an Accurate Benchmark for Broad-Coverage Biomedical Relation Extraction, Proceedings of The 29th International Conference on Computational Linguistics (Coling-2022), October 12-17, 2022, Gyeongju, Republic of Korea
  • Ioannis Dikeoulias, Saadullah Amin, and Günter Neumann (2022) Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic Representations , Proceedings of the 7th Workshop on Representation Learning for NLP. ACL-2022, RepL4NLP May 2022, Pages 111-120 ACL 5/2022 (RepL4NLP-2022), May, 2022.
  • Saadullah Amin, Noon Pokaratsiri, Morgan Wixted, Alejandro García-Rudolph, Catalina Martínez-Costa, and Günter Neumann (2022) Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts , Proceedings of the 21st Workshop on Biomedical Language Processing. ACL-2022 BioNLP, May 22-27, Pages 200-211 ACL 5/2022. (BioNLP-2022), May, 2022

Links

Overview

MT Team

E&E Team

TR Team

QAIE Members

Team Lead:

Prof. Dr. Günter Neumann 

Team Members:

Yasser Hamidullah
Nicholas Jennings
Aravind Krishnan
Cennet Oguz
Jörg Steffen
Noon Pokaratsiri
 

Master Students and Research Assistants:

Betül Bahceci
Katja Konermann
Eduardo Venegas