We introduce the EPOP (Epidemiomonitoring of Plants) corpus, a new annotated resource for structured information extraction in the domain of plant health epidemiology. The corpus consists of translated news reports that reflect real-world phytosanitary monitoring scenarios. It includes annotations for named entities (e.g. Plant, Pest, Vector, Disease, Dissemination Pathway), identity coreferences, and both binary and complex n-ary relations that represent key events such as Transmits or Causes, along with their modalities. A distinctive feature of EPOP is its normalization layer where mentions of species and geographical locations are linked to canonical identifiers in the NCBI Taxonomy and GeoNames, enabling semantic disambiguation and integration with external knowledge bases. As the first publicly available corpus of its kind, EPOP presents a realistic and challenging benchmark, with high linguistic variability, entity role ambiguity, and long-distance relations. We report baseline results on core tasks (named entity recognition, normalization (entity-linking), and relation extraction) using both fine-tuned BERT-based models and hard-prompted large language models. These experiments demonstrate the utility of EPOP while also identifying areas for improvement, particularly in the extraction of complex relations. The corpus is released under an open license, to support research in environmental NLP, crop protection, and knowledge graph enrichment.

Retrieval-augmented generation (RAG) is increasingly popular in information extraction (IE), especially in biological and chemical domains where external knowledge is abundant. Existing RAG-enhanced IE systems, however, typically retrieve for every input, even though retrieval may be unnecessary, introduce distracting evidence, and increase inference cost. To address this issue, we propose RAG Switch, a retrieval decision framework for IE that combines difficulty-aware signals with task-grounded supervision. Specifically, we approximate model-specific training difficulty, quantified by Error L2-Norm (EL2N), from inference-time uncertainty signals, and use it to guide retrieval decisions. We then define retrieval necessity directly from instance-level extraction outcomes without retrieval, yielding task-grounded supervision for learning retrieval decision. Experiments on multiple biological and chemical IE benchmarks across diverse IE backbones show that RAG Switch consistently outperforms representative retrieval decision baselines and achieves a strong efficiency–performance trade-off in end-to-end RAG-enhanced IE pipelines.

Generative methods have recently gained traction in biological and chemical named entity recognition for their ability to overcome tagging limitations and better capture entity-rich contexts. However, under a few-shot environment, they struggle with the scarcity of annotated data and the structural complexity of biological and chemical entities—particularly nested and discontinuous ones—leading to incorrect recognition and error propagation during generation. To address these challenges, we propose SCoNE, a Self-Correcting and Noise-Augmented Method for Complex Biological and Chemical Named Entity Recognition. Specifically, we introduce a Noise Augmentation Module to enhance training diversity and guide the model to better learn complex entity structures. Besides, we design a Confidence-based Self-Correction Module that identifies low-confidence outputs and revises them to improve generation robustness. Benefiting from these designs, our method outperforms the baselines by 1.80 and 2.73 F1-score on the CHEMDNER and microbial ecology dataset Florilege, highlighting its effectiveness in biological and chemical named entity recognition.

Understanding how scientific findings are discussed and evaluated over time provides valuable evidence for assessing their reliability. We propose the Rhetorical Citation Graph (RCG), a finding-centric graph model that represents citation events by explicitly linking scientific findings, citing articles, rhetorical functions, and citation contexts. We instantiate this model as the Plant Literature Reliability Network (PLIN), a graph of 262,807 citation events automatically constructed from the plant-health literature using Natural Language Processing methods for citation and finding extraction, and rhetorical stance classification. By integrating provenance data with the rhetorical interpretation expressed in citation contexts, the RCG provides structured evidence for contextual analyses of scientific findings and lays the foundation for longitudinal studies of their evolution, scientific consensus, and reliability. Finally, we illustrate the utility of PLIN through a case study on the curation and enrichment of the EPPO Global Database, a reference knowledge base for plant health.

La classification automatique des fonctions rhétoriques des citations contribue à l’étude des stratégies discursives d’un auteur lorsqu’il cite, et plus généralement, de son intention. Dans l’objectif d’estimer la fiabilité des découvertes citées en écologie, cet article analyse les capacités de transfert des modèles de langue affinés en linguistique computationnelle pour cette tâche, en les comparant aux méthodes par amorçage (prompting). Nous introduisons PD100cit, un nouveau corpus annoté, ainsi qu’un guide d’annotation, afin d’explorer la typologie rhétorique des citations relatives aux interactions biologiques. Nous explorons également la sensibilité des modèles aux longueurs des contextes des passages de citations. Nos résultats montrent de bonnes performances des modèles de langue transférés en écologie et l’intérêt de réviser la typologie pour évaluer la fiabilité des découvertes de la linguistique computationnelle à l’écologie.

L’intégration de connaissances externes dans les modèles neuronaux est très étudiée pour améliorer les performances des modèles de langue pré-entraînés, notamment en domaine biomédical. Dans cet article, nous explorons la contribution de plongements de bases de connaissances à une tâche d’extraction de relations. Pour deux mentions d’entités candidates dans un texte, nous faisons l’hypothèse que la connaissance de relations entre elles, issue d’une base de connaissances (BC) externe, aide à prédire l’existence d’une relation dans le texte, y compris lorsque les relations de BC sont différentes de celles du texte. Notre approche consiste à calculer des plongements du graphe de BC et à estimer la possibilité pour chaque paire d’entité du texte qu’elle soit reliée par une relation de BC. Les expériences menées sur trois tâches d’extraction de relations en domaine biomédical montrent que notre méthode surpasse le modèle PubMedBERT de base et donne des performances comparables aux méthodes de l’état de l’art.

Entity normalization (or entity linking) is an important subtask of information extraction that links entity mentions in text to categories or concepts in a reference vocabulary. Machine learning based normalization methods have good adaptability as long as they have enough training data per reference with a sufficient quality. Distributional representations are commonly used because of their capacity to handle different expressions with similar meanings. However, in specific technical and scientific domains, the small amount of training data and the relatively small size of specialized corpora remain major challenges. Recently, the machine learning-based CONTES method has addressed these challenges for reference vocabularies that are ontologies, as is often the case in life sciences and biomedical domains. And yet, its performance is dependent on manually annotated corpus. Furthermore, like other machine learning based methods, parametrization remains tricky. We propose a new approach to address the scarcity of training data that extends the CONTES method by corpus selection, pre-processing and weak supervision strategies, which can yield high-performance results without any manually annotated examples. We also study which hyperparameters are most influential, with sometimes different patterns compared to previous work. The results show that our approach significantly improves accuracy and outperforms previous state-of-the-art algorithms.

This paper presents the fourth edition of the Bacteria Biotope task at BioNLP Open Shared Tasks 2019. The task focuses on the extraction of the locations and phenotypes of microorganisms from PubMed abstracts and full-text excerpts, and the characterization of these entities with respect to reference knowledge sources (NCBI taxonomy, OntoBiotope ontology). The task is motivated by the importance of the knowledge on biodiversity for fundamental research and applications in microbiology. The paper describes the different proposed subtasks, the corpus characteristics, and the challenge organization. We also provide an analysis of the results obtained by participants, and inspect the evolution of the results since the last edition in 2016.