AgriLens: Semantic Retrieval in Agricultural Texts Using Topic Modeling and Language Models
This work addresses the need for efficient information retrieval in specialized domains like agriculture, where data is often unlabeled, though it is incremental as it builds on existing methods like BERTopic.
The paper tackled the problem of organizing and retrieving information from unstructured agricultural texts by developing a framework that combines topic modeling and language models for interpretable topic extraction and semantic retrieval, achieving scalable access without requiring labeled data.
As the volume of unstructured text continues to grow across domains, there is an urgent need for scalable methods that enable interpretable organization, summarization, and retrieval of information. This work presents a unified framework for interpretable topic modeling, zero-shot topic labeling, and topic-guided semantic retrieval over large agricultural text corpora. Leveraging BERTopic, we extract semantically coherent topics. Each topic is converted into a structured prompt, enabling a language model to generate meaningful topic labels and summaries in a zero-shot manner. Querying and document exploration are supported via dense embeddings and vector search, while a dedicated evaluation module assesses topical coherence and bias. This framework supports scalable and interpretable information access in specialized domains where labeled data is limited.