Domain Adaptation in Nested Named Entity Recognition From Scientific Articles in Agriculture

Abstract

In the realm of digital agriculture, the ability to make timely, profitable, and actionable decisions depends on agronomists using agricultural data and related cultivated data, including text sources such as news articles, farm notes, and agricultural scientific reports. Named entity recognition (NER) and agricultural entity recognition (AGER) facilitate semantic understanding, enabling precise identification, categorization of farming components, and knowledge discovery. However, current approaches to agricultural entity recognition encounter limitations due to limited resources. Moreover, the necessity to identify nested named entities emerges from the complexities inherent in the agricultural domain. Relevant information often traverses multiple interconnected elements rather than residing as isolated entities. For instance, comprehending a target farming practice might necessitate pinpointing the crop, the associated nutrients, or diseases - each constituting a nested entity within a broader context. Consequently, agricultural entity recognition from unstructured text gives high importance to information retrieval and knowledge construction within this domain. This study constructs the SAGRI dataset, incorporating a novel tagset for AGER that encompasses prevalent agricultural and scientific concepts, methodically established through annotation. This tagset enables the extraction of domain-independent concepts from scientific article abstracts. This study also introduces a cutting-edge deep learning baseline with an advanced Triaffine attention mechanism for robust entity extraction. Additionally, it presents a pioneering few-shot learning strategy that optimizes cross-domain categorization, mainly when dealing with scarce training data. Notably, this strategy achieves high F1 scores compared to the baseline, underscoring its potential to curtail required training data considerably.