Günter Neumann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Günter Neumann has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Stalin Varanasi
University of Saarland
3 shared publications - Umer Butt
University of Saarland
3 shared publications - Saadullah Amin2 shared publications
- Alejandro García-Rudolph
Department of Research and Innovation, Institut Guttmann, Institut Universitari de Neurorehabilitació adscrit a la UAB, Badalona, Barcelona, Spain
1 shared publication Aleksandra Gabryszak
German Research Center for Artificial Intelligence (DFKI), Berlin
1 shared publication- Andreas Buerkert
Organic Plant Production and Agroecosystems Research in the Tropics and Subtropics (OPATS), University of Kassel, Witzenhausen, Germany
1 shared publication
Latest Publications
- Open Access
- 3 April 2025
- Published by Springer Nature
- p. C1
Correction to: Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO
- 3 April 2025
- Published by Springer Nature
- p. C1
Open AccessCorrection to: Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO
- 3 April 2025
- Published by Springer Nature
- p. 282-289
Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO
- 3 April 2025
- Published by Springer Nature
- p. 282-289
Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 144-153
Low-Resource Transliteration for Roman-Urdu and Urdu Using Transformer-Based Models
Umer Butt, Stalin Varanasi, Günter Neumann. Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 144-153
Open AccessLow-Resource Transliteration for Roman-Urdu and Urdu Using Transformer-Based Models
Umer Butt, Stalin Varanasi, Günter Neumann. Proceedings of the Eighth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2025). 2025.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 78-92
Towards Understanding Attention-based Reasoning through Graph Structures in Medical Codes Classification
Noon Goldstein, Saadullah Amin, Günter Neumann. Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 78-92
Open AccessTowards Understanding Attention-based Reasoning through Graph Structures in Medical Codes Classification
Noon Goldstein, Saadullah Amin, Günter Neumann. Proceedings of TextGraphs-17: Graph-based Methods for Natural Language Processing. 2024.
- Open Access
Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic Representations
Temporal knowledge graph completion (TKGC) has become a popular approach for reasoning over the event and temporal knowledge graphs, targeting the completion of knowledge with accurate but missing information. In this context, tensor decomposition has successfully modeled interactions between entities and relations. Their effectiveness in static knowledge graph completion motivates us to introduce Time-LowFER, a family of parameter-efficient and time-aware extensions of the low-rank tensor factorization model LowFER. Noting several limitations in current approaches to represent time, we propose a cycle-aware time-encoding scheme for time features, which is model-agnostic and offers a more generalized representation of time. We implement our methods in a unified temporal knowledge graph embedding framework, focusing on time-sensitive data processing. The experiments show that our proposed methods perform on par or better than the state-of-the-art semantic matching models on two benchmarks.
Open AccessTemporal Knowledge Graph Reasoning with Low-rank and Model-agnostic Representations
Temporal knowledge graph completion (TKGC) has become a popular approach for reasoning over the event and temporal knowledge graphs, targeting the completion of knowledge with accurate but missing information. In this context, tensor decomposition has successfully modeled interactions between entities and relations. Their effectiveness in static knowledge graph completion motivates us to introduce Time-LowFER, a family of parameter-efficient and time-aware extensions of the low-rank tensor factorization model LowFER. Noting several limitations in current approaches to represent time, we propose a cycle-aware time-encoding scheme for time features, which is model-agnostic and offers a more generalized representation of time. We implement our methods in a unified temporal knowledge graph embedding framework, focusing on time-sensitive data processing. The experiments show that our proposed methods perform on par or better than the state-of-the-art semantic matching models on two benchmarks.
- Open Access
Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts
Despite the advances in digital healthcare systems offering curated structured knowledge, much of the critical information still lies in large volumes of unlabeled and unstructured clinical texts. These texts, which often contain protected health information (PHI), are exposed to information extraction tools for downstream applications, risking patient identification. Existing works in de-identification rely on using large-scale annotated corpora in English, which often are not suitable in real-world multilingual settings. Pre-trained language models (LM) have shown great potential for cross-lingual transfer in low-resource settings. In this work, we empirically show the few-shot cross-lingual transfer property of LMs for named entity recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan) clinical notes de-identification in the stroke domain. We annotate a gold evaluation dataset to assess few-shot setting performance where we only use a few hundred labeled examples for training. Our model improves the zero-shot F1-score from 73.7% to 91.2% on the gold evaluation set when adapting Multilingual BERT (mBERT) (Devlin et al., 2019) from the MEDDOCAN (Marimon et al., 2019) corpus with our few-shot cross-lingual target corpus. When generalized to an out-of-sample test set, the best model achieves a human-evaluation F1-score of 97.2%.
Open AccessFew-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts
Despite the advances in digital healthcare systems offering curated structured knowledge, much of the critical information still lies in large volumes of unlabeled and unstructured clinical texts. These texts, which often contain protected health information (PHI), are exposed to information extraction tools for downstream applications, risking patient identification. Existing works in de-identification rely on using large-scale annotated corpora in English, which often are not suitable in real-world multilingual settings. Pre-trained language models (LM) have shown great potential for cross-lingual transfer in low-resource settings. In this work, we empirically show the few-shot cross-lingual transfer property of LMs for named entity recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan) clinical notes de-identification in the stroke domain. We annotate a gold evaluation dataset to assess few-shot setting performance where we only use a few hundred labeled examples for training. Our model improves the zero-shot F1-score from 73.7% to 91.2% on the gold evaluation set when adapting Multilingual BERT (mBERT) (Devlin et al., 2019) from the MEDDOCAN (Marimon et al., 2019) corpus with our few-shot cross-lingual target corpus. When generalized to an out-of-sample test set, the best model achieves a human-evaluation F1-score of 97.2%.
- Open Access
A Data-driven Approach for Noise Reduction in Distantly Supervised Biomedical Relation Extraction
Fact triples are a common form of structured knowledge used within the biomedical domain. As the amount of unstructured scientific texts continues to grow, manual annotation of these texts for the task of relation extraction becomes increasingly expensive. Distant supervision offers a viable approach to combat this by quickly producing large amounts of labeled, but considerably noisy, data. We aim to reduce such noise by extending an entity-enriched relation classification BERT model to the problem of multiple instance learning, and defining a simple data encoding scheme that significantly reduces noise, reaching state-of-the-art performance for distantly-supervised biomedical relation extraction. Our approach further encodes knowledge about the direction of relation triples, allowing for increased focus on relation learning by reducing noise and alleviating the need for joint learning with knowledge graph completion.
Open AccessA Data-driven Approach for Noise Reduction in Distantly Supervised Biomedical Relation Extraction
Fact triples are a common form of structured knowledge used within the biomedical domain. As the amount of unstructured scientific texts continues to grow, manual annotation of these texts for the task of relation extraction becomes increasingly expensive. Distant supervision offers a viable approach to combat this by quickly producing large amounts of labeled, but considerably noisy, data. We aim to reduce such noise by extending an entity-enriched relation classification BERT model to the problem of multiple instance learning, and defining a simple data encoding scheme that significantly reduces noise, reaching state-of-the-art performance for distantly-supervised biomedical relation extraction. Our approach further encodes knowledge about the direction of relation triples, allowing for increased focus on relation learning by reducing noise and alleviating the need for joint learning with knowledge graph completion.
- 2 July 2014
- Published by Springer Nature
- p. 383-392
Linguistics to Structure Unstructured Information
- Open Access
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 69-74
An analysis of textual inference in German customer emails
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 69-74
Open AccessAn analysis of textual inference in German customer emails