EnterpriseEM: Fine-tuned Embeddings for Enterprise Semantic Search
Kamalkumar Rathinasamy, Jayarama Nettar, Amit Kumar, Vishal Manchanda, Arun Vijayakumar, Ayush Kataria, Venkateshprasanna Manjunath, Chidambaram GS, Jaskirat Singh Sodhi, Shoeb Shaikh, Wasim Akhtar Khan, Prashant Singh, Tanishq Dattatray Ige, Vipin Tiwari, Rajab Ali Mondal, Harshini K, S Reka, Chetana Amancharla, Faiz ur Rahman, Harikrishnan P A, Indraneel Saha, Bhavya Tiwary, Navin Shankar Patel, Pradeep T S, Balaji A J, Priyapravas, Mohammed Rafee Tarafdar
TL;DR
The paper tackles enterprise information retrieval over proprietary unstructured data and the misalignment of generic embeddings. It proposes EnterpriseEM, a pipeline to fine-tune embeddings on enterprise corpora, and augments it with synthetic domain-specific QA generated with custom-entity annotations. BeIR-based evaluation shows fine-tuned bi-encoders and rerankers outperform pre-trained baselines, achieving higher NDCG@3, MAP@3, and precision. The work demonstrates a practical path to improved enterprise search and suggests directions for semantic chunking, cross-domain generalization, and multimedia data extraction.
Abstract
Enterprises grapple with the significant challenge of managing proprietary unstructured data, hindering efficient information retrieval. This has led to the emergence of AI-driven information retrieval solutions, designed to adeptly extract relevant insights to address employee inquiries. These solutions often leverage pre-trained embedding models and generative models as foundational components. While pre-trained embeddings may exhibit proximity or disparity based on their original training objectives, they might not fully align with the unique characteristics of enterprise-specific data, leading to suboptimal alignment with the retrieval goals of enterprise environments. In this paper, we propose a comprehensive methodology for contextualizing pre-trained embedding models to enterprise environments, covering the entire process from data preparation to model fine-tuning and evaluation. By adapting the embeddings to better suit the retrieval tasks prevalent in enterprises, we aim to enhance the performance of information retrieval solutions. We discuss the process of fine-tuning, its effect on retrieval accuracy, and the potential benefits for enterprise information management. Our findings demonstrate the efficacy of fine-tuned embedding models in improving the precision and relevance of search results in enterprise settings.