Multilinguality and Language Technology

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

Question Answering (finding and extracting answers for natural language questions from text) and Information Extraction (extracting entities and relations from text) are closely related: both share a number of sub-tasks like named entity recognition, relation extraction and entity linking. 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.

• Stalin Varanasi, Saadullah Amin and Günter Neumann (2021) AutoEQA: Auto-Encoding Questions for Extractive Question Answering, In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP-2021), Nov. 2021.
• Saadullah Amin, Günter Neumann (2021) T2NER: Transformers based transfer learning framework for named entity recognition, In Proceedings of EACL, 2021.
• Saadullah Amin, Stalin Varanasi, Katherine Dunfield, Günter Neumann (2020) LowFER: Low-rank Bilinear Pooling for Link Prediction. In: Proceedings of the 37th International Conference on Machine Learning (ICML-2020), Online, PMLR 119, 2020.
• Saadullah Amin, Katherine Dunfield, Anna Vechkaeva, Günter Neumann (2020) A Data-driven Approach for Noise Reduction in Distantly Supervised Biomedical Relation Extraction. In: BioNLP 2020 Workshop on Biomedical Natural Language Processing. Workshop on Current Trends in Biomedical Natural Language Processing (BioNLP-2020) located at The 58th Annual Meeting of the Association for Computational Linguistics July 9-9 ACL 2020.
• Stalin Varanasi, Saadullah Amin, Günter Neumann (2020) CopyBERT: A Unified Approach to Question Generation with Self-Attention. In: NLP for Conversational AI - Proceedings of the 2nd Workshop. NLP for Conversational AI (NLPConvAI-2020) July 9-9 Pages 25-31 ISBN 978-1-952148-08-8 ACL 2020.