Enhancing Plant Species Retrieval in Flora Through Language Model Integration

Le résumé fourni par la source

Traditionally, textual data storage and retrieval systems were designed primarily for human reading, mainly relying on paper records. However, as information technology has advanced, computerized searches have become common. However, Boolean logic-based data retrieval systems often struggle to handle data's diversity and richness effectively. These systems rely on strict matching rules, which can lead to either too few or too many results. For example, when searching for plant species descriptions, a query like "circle" AND "ellipse" may exclude relevant records that describe these traits using slightly different terms (e.g., "round" or "oval"). Conversely, broader queries like "oblong" may return an overwhelming number of irrelevant results. This rigidity limits the system's ability to adapt to the nuanced and varied ways users describe data. With the advent of advanced semantic models such as SBERT (Sentence-Bidirectional Encoder Representations from Transformers) (Reimers and Gurevych 2019), we can now delve deeper into the semantic relationships within textual data. Unlike general-purpose large language models, SBERT is specifically designed for efficient semantic similarity computation. In plant taxonomy, records in Flora, such as Flora of Taiwan or Flora of China, play a crucial role in understanding plant diversity in specific regions. These records provide critical information on plant growth environments, morphological characteristics, and economic values. Our research aims to enhance the efficiency of retrieving plant data using language models. Specifically, we transform textual descriptions from Flora and user queries into vector representations (Fig. 2) and calculate their cosine similarity to determine the relevance between user inputs and species records. Cosine similarity, a metric commonly used in text mining and information retrieval, quantifies the similarity between two vectors by measuring the cosine of the angle between them. The similarity score ranges from -1 (completely dissimilar) to 1 (identical), where higher scores indicate greater similarity. By applying this method, we can provide users with ranked scores of plant species related to their queries (Fig. 1). This approach not only streamlines data retrieval but also introduces new perspectives for botanical research and data management, fostering a more efficient exploration of plant diversity. Our results demonstrate the potential of language models to facilitate biodiversity research and data management, especially in retrieving plant taxonomy information. Our approach provides a novel tool for future biodiversity data analysis and retrieval, thereby contributing to the progress of biodiversity conservation.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.