PUBLICATIONS

@inproceedings{Hammerla:Mehler:2026:a,

title = {Gutenberg+: A More Temporally Faithful Corpus for Diachronic NLP},

author = {Leon Hammerla and Alexander Mehler},

year  = {2026},

date = {2026-01-01},

booktitle = {Proceedings Workshop on Structured Linguistic Data and Evaluation 

 (SLiDE 2026), co-located with the Language Resources and Evaluation 

 Conference (LREC 2026)},

address = {Palma de Mallorca (Spain)},

note = {accepted},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Abusaleh:et:al:2026,

title = {Learning to Detect Cross-Modal Negation: An Analysis of Latent 

 Representations and an Attention-Based Solution},

author = {Ali Abusaleh and Leon Hammerla and Alexander Mehler},

year  = {2026},

date = {2026-01-01},

booktitle = {2026 8th International Conference on Natural Language Processing (ICNLP)},

address = {Xi'an,China},

abstract = {Detecting high-level semantic concepts like negation across modalities 

 remains a challenge for current multimodal systems. We analyze 

 this as a fundamental representation learning problem, providing 

 the first evidence that negation does not form a linearly or non-linearly 

 separable class in the latent spaces of standard vision-language 

 models (VLMs). We demonstrate that pretrained embeddings primarily 

 encode modality-specific features, lacking a generalizable negation 

 signal. To overcome this, we propose a novel cross-modal attention 

 architecture that explicitly models inter-modal dependencies, 

 achieving performance gains of up to +7.03% F1 over unimodal baselines. 

 Our analysis reveals a key asymmetry: while textual negation often 

 appears independently, visual negation is semantically dependent 

 on linguistic context, a finding validated through our statistical 

 analysis of 3,222 political video-text pairs automatically annotated 

 via Qwen2.5-VL. By combining this analysis with self-supervised 

 video representations (JEPA2), we advance the modeling of temporal 

 negation. This work provides new methods and insights for learning 

 robust, semantically-aligned representations in multimodal systems.},

note = {accepted},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Luecking:Hammerla:Mehler:2026,

title = {Not every quantifier can be negated},

author = {Andy Lücking and Leon Hammerla and Alexander Mehler},

year  = {2026},

date = {2026-01-01},

booktitle = {Proceedings of textitSinn und Bedeutung, Special Session ``Philosophical 

 and Linguistic Approaches to Negation (PhilLingNeg)''},

address = {Frankfurt am Main},

series = {SuB'30},

note = {accepted},

keywords = {},

pubstate = {forthcoming},

tppubtype = {inproceedings}

}

@inproceedings{Hammerla:Mehler:2026:b,

title = {Negation in Reasoning Traces: Interpretable Signals of Correctness 

 and Provenance},

author = {Leon Hammerla and Alexander Mehler},

year  = {2026},

date = {2026-01-01},

booktitle = {Proceedings of the 6th Workshop on Natural Logic Meets Machine Learning (NALOMA)},

address = {Prague (Czech Republic)},

note = {accepted},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Hammerla:et:al:2025b,

title = {D-Neg: Syntax-Aware Graph Reasoning for Negation Detection},

author = {Leon Hammerla and Andy Lücking and Carolin Reinert and Alexander Mehler},

editor = {Kentaro Inui and Sakriani Sakti and Haofen Wang and Derek F. Wong and Pushpak Bhattacharyya and Biplab Banerjee and Asif Ekbal and Tanmoy Chakraborty and Dhirendra Pratap Singh},

url = {https://aclanthology.org/2025.findings-ijcnlp.89/},

isbn = {979-8-89176-303-6},

year  = {2025},

date = {2025-12-01},

booktitle = {Proceedings of the 14th International Joint Conference on Natural 

 Language Processing and the 4th Conference of the Asia-Pacific 

 Chapter of the Association for Computational Linguistics},

pages = {1432–1454},

publisher = {The Asian Federation of Natural Language Processing and The Association for Computational Linguistics},

address = {Mumbai, India},

abstract = {Despite the communicative importance of negation, its detection 

 remains challenging. Previous approaches perform poorly in out-of-domain 

 scenarios, and progress outside of English has been slow due to 

 a lack of resources and robust models. To address this gap, we 

 present D-Neg: a syntax-aware graph reasoning model based on a 

 transformer that incorporates syntactic embeddings by attention-gating. 

 D-Neg uses graph attention to represent syntactic structures, 

 emulating the effectiveness of rule-based dependency approaches 

 for negation detection. We train D-Neg using 7 English resources 

 and their translations into 10 languages, all aligned at the annotation 

 level. We conduct an evaluation of all these datasets in in-domain 

 and out-of-domain settings. Our work represents a significant 

 advance in negation detection, enabling more effective cross-lingual 

 research.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Hammerla:et:al:2025a,

title = {Standardizing Heterogeneous Corpora with DUUR: A Dual Data- 

 and Process-Oriented Approach to Enhancing NLP Pipeline Integration},

author = {Leon Hammerla and Alexander Mehler and Giuseppe Abrami},

editor = {Kentaro Inui and Sakriani Sakti and Haofen Wang and Derek F. Wong and Pushpak Bhattacharyya and Biplab Banerjee and Asif Ekbal and Tanmoy Chakraborty and Dhirendra Pratap Singh},

url = {https://aclanthology.org/2025.findings-ijcnlp.87/},

isbn = {979-8-89176-303-6},

year  = {2025},

date = {2025-12-01},

booktitle = {Proceedings of the 14th International Joint Conference on Natural 

 Language Processing and the 4th Conference of the Asia-Pacific 

 Chapter of the Association for Computational Linguistics},

pages = {1410–1425},

publisher = {The Asian Federation of Natural Language Processing and The Association for Computational Linguistics},

address = {Mumbai, India},

abstract = {Despite their success, LLMs are too computationally expensive 

 to replace task- or domain-specific NLP systems. However, the 

 variety of corpus formats makes reusing these systems difficult. 

 This underscores the importance of maintaining an interoperable 

 NLP landscape. We address this challenge by pursuing two objectives: 

 standardizing corpus formats and enabling massively parallel corpus 

 processing. We present a unified conversion framework embedded 

 in a massively parallel, microservice-based, programming language-independent 

 NLP architecture designed for modularity and extensibility. It 

 allows for the integration of external NLP conversion tools and 

 supports the addition of new components that meet basic compatibility 

 requirements. To evaluate our dual data- and process-oriented 

 approach to standardization, we (1) benchmark its efficiency in 

 terms of processing speed and memory usage, (2) demonstrate the 

 benefits of standardized corpus formats for NLP downstream tasks, 

 and (3) illustrate the advantages of incorporating custom formats 

 into a corpus format ecosystem.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Bundan:Abrami:Mehler:2025,

title = {Multimodal Docker Unified UIMA Interface: New Horizons for Distributed 

 Microservice-Oriented Processing of Corpora using UIMA},

author = {Daniel Bundan and Giuseppe Abrami and Alexander Mehler},

editor = {Christian Wartena and Ulrich Heid},

url = {https://aclanthology.org/2025.konvens-1.22/},

year  = {2025},

date = {2025-01-01},

booktitle = {Proceedings of the 21st Conference on Natural Language Processing 

 (KONVENS 2025): Long and Short Papers},

pages = {257–268},

publisher = {HsH Applied Academics},

address = {Hildesheim, Germany},

series = {KONVENS '25},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}