Enhancing query relevance: leveraging SBERT and cosine similarity for optimal information retrieval

被引:1
|
作者
Venkatesh Sharma, K. [1 ]
Ayiluri, Pramod Reddy [2 ]
Betala, Rakesh [3 ]
Jagdish Kumar, P. [4 ]
Shirisha Reddy, K. [2 ]
机构
[1] CVR College of Engineering, TS, Mangalpalle, Rangareddy, India
[2] Department of CSE, TKR College of Engineering Technology, Saroor Nagar, Telangana, Hyderabad,500097, India
[3] Engineering Department, University of Technology and Applied Sciences-AlMusannah, AlMusannah, Oman
[4] Department of CSE-AI & amp,DS, FST IFHE ICFAI UNIVERSITY Shankarpally, Hyderabad, India
关键词
Encode; Pooling; Cosine similarity; Embeddings;
D O I
10.1007/s10772-024-10133-5
中图分类号
学科分类号
摘要
Whether the information is related to a concept or a product, queries are frequently employed to find out information. Different people will use different sentences while having the same objective. In our research, we generated a sentence vector using an SBERT-based model called all-MiniLM-L6-v2, which is a MiniLM model calibrated on a sizable dataset of more than 1 billion training pairings. Then, we compute a similarity score using these vectors to determine how similar the provided query is to other queries previously stored within the database. Cosine similarity is the metric used to assess similarity in our work. From the pool of potential answers, we will choose the one that has the highest similarity score with its query. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.
引用
收藏
页码:753 / 763
页数:10
相关论文
共 39 条