QUERY-TYPE SENSITIVITY AND SELECTIVE BENEFITS OF HYBRID LEXICAL- SEMANTIC RETRIEVAL: AN EXPERIMENTAL ANALYSIS WITH BM25 AND MULTILINGUAL SBERT
- Departement Informatique et Science du Numerique, Unite de Recherche et d’Expertise Numerique, Universite Virtuelle de Cote d Ivoire, UVCI, Abidjan, Cote d Ivoire.
- Laboratoire de Recherche en Informatique et Telecommunication (LARIT), Institut National Polytechnique Felix Houphouet-Boigny (INPHB), Yamoussoukro, Cote d Ivoire.
0 Downloads
9 Views
Abstract
Hybrid lexical-semantic retrieval combines signals derived from explicit term matching and dense semantic representations. However, an aggregate retrieval score can conceal heterogeneous behavior across information needs. This study examines that heterogeneity at query and predefined query-type levels using a controlled university information-retrieval benchmark of 50 queries and 19 documents, corresponding to 950 query-document pairs. Four retrieval conditions are evaluated descriptively: BM25, multilingual SBERT, Reciprocal Rank Fusion (RRF), and normalized lexical-semantic score fusion with a fixed weight a=0.5.
Keywords
How to Cite This Article
Mamadou Bakouan et, al (2026); QUERY-TYPE SENSITIVITY AND SELECTIVE BENEFITS OF HYBRID LEXICAL- SEMANTIC RETRIEVAL: AN EXPERIMENTAL ANALYSIS WITH BM25 AND MULTILINGUAL SBERT, International Journal of Advanced Research (IJAR), 14 (08), 1189-1195, ISSN 2320-5407. DOI: https://doi.org/10.21474/IJAR01/24038
Corresponding Author
Publication Achievement
Publication card
🎉 Proud to contribute to scientific research! Share your publication with your colleagues and professional network.
Article Analytics
This work is licensed under a Creative Commons Attribution 4.0 International License.





