Query Attribute Modeling: Improving Search Relevance with Semantic Search and Meta Data Filtering
Abstract
The exponential growth of e-commerce has created vast product catalogs where traditional keyword, semantic or hybrid search struggles to balance precision with relevance, frequently overlooking attribute constraints or misinterpreting user intent. This study introduces Query Attribute Modeling (QAM), a hybrid framework that enhances search precision and relevance through a two-step process. First, item descriptions and titles are decomposed into structured attributes and stored as metadata key-value pairs alongside item description embeddings. Second, QAM decomposes open text queries into structured metadata tags and semantic elements, enabling focused retrieval by automatically extracting metadata filters from free-form text queries and reducing noise. Experimental evaluation using the Amazon Toys Reviews dataset (10,000 unique items with 40,000+ reviews and detailed product attributes) demonstrated QAM's superior performance, achieving a mean average precision at 5 (mAP@5) of 52.99%. QAM showed substantial improvements: 28.67% over BM25 keyword-based search, 6.5% over semantic search, 8.58% over cross-encoder reranking, and 9.96% over hybrid search combining encoder embeddings and BM25 results using Reciprocal Rank Fusion. The results establish QAM as a robust solution for Enterprise Search applications, particularly in e-commerce systems.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cited works that were retracted
Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.
Cites a retracted work: 10.1109/peeic59336.2023.10451301
InfoThe cited work was retracted on 2026-10-23 (notice 10.1109/peeic59336.2023.11752266), not before this paper was published (2025-11-12).
Cited work 10.1109/peeic59336.2023.10451301 · retracted 2026-10-23 · notice 10.1109/peeic59336.2023.11752266 · this paper published 2025-11-12
“10.1109/PEEIC59336.2023.10451301”
Cites
1 retracted
Scaling AI-Driven Solutions for Semantic Search
Srivastava, A., Nalluri, M., Lata, T., et al. (2023) · doi:10.1109/peeic59336.2023.10451301 · Cited by 13 · see citing works
RetractedThe probabilistic relevance framework: BM25 and beyond
Robertson, S., & Zaragoza, H. (2009) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000019 · Cited by 3,374 · see citing works
AbuKausar, M., Dhaka, V. S., & Singh, S. K. (2013) · International Journal of Computer Applications · doi:10.5120/10440-5125 · Cited by 98 · see citing works
Learning and Representing Verbal Meaning
Landauer, T. K. (1998) · Current Directions in Psychological Science · doi:10.1111/1467-8721.ep10836862 · Cited by 93 · see citing works
Understanding the Nature of Metadata: Systematic Review
Ulrich, H., Kock-Schoppenhauer, A.-K., Deppenwiese, N., Gött, R., Kern, J., Lablans, M., Majeed, R. W., Stöhr, M. R., Stausberg, J., Varghese, J., et al. (2021) · Journal of Medical Internet Research · doi:10.2196/25440 · Cited by 92 · see citing works
Complement Lexical Retrieval Model with Semantic Residual Embeddings
Gao, L., Dai, Z., Chen, T., Fan, Z., Durme, B. V., & Callan, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72113-8_10 · Cited by 91 · see citing works
Large language model applications for evaluation: Opportunities and ethical implications
Head, C. B., Jasper, P., McConnachie, M. M., Raftree, L., & Higdon, G. L. (2023) · New Directions for Evaluation · doi:10.1002/ev.20556 · Cited by 85 · see citing works
Evaluation in information retrieval
Manning, C. D., Raghavan, P., & Schütze, H. (2008) · Cambridge University Press eBooks · doi:10.1017/cbo9780511809071.009 · Cited by 71 · see citing works
Nussbaum, Z., Morris, J. X., Duderstadt, B., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.01613 · Cited by 28 · see citing works
Tannebaum, W., & Rauber, A. (2015) · World Patent Information · doi:10.1016/j.wpi.2015.02.005 · Cited by 8 · see citing works
Improving Web Search Using Contextual Retrieval
Limbu, D. K., Connor, A. M., Pears, R., & MacDonell, S. G. (2009) · International Conference on Information Technology: New Generations · doi:10.1109/itng.2009.133 · Cited by 7 · see citing works
Semantic Web Search Engines : A Comparative Survey
Kumari, A., & Thakur, J. (2019) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit195115 · Cited by 7 · see citing works
An Empirical Study of Uniform-Architecture Knowledge Distillation in Document Ranking
Qin, X.-B., Liu, X., Zheng, X.-F., Liu, J., & Zhu, Y.-T. (2023) · arXiv.org · doi:10.48550/arxiv.2302.04112 · Cited by 1
Flagged first, then by citations
Research works printed but not linked: 6
- Excite - web portal and search engine
- Webcrawler - search engine
- Redonnet, 2024, TexLexAn: An open source automatic text summarizer
- 2024, Gpt-4o system card
- Face, Cross-encoder/msmarco-minilm-112-en-de-v1
- 2024, Qdrant documentation
Cited by
Still being checked.
- Authors
- Menon, K., Haider, B. A., Arham, M., Mehreen, K., Kadiyala, R. M. R., Shafique, M. A., & Farooq, H.
- Affiliations
- traversaal.ai,USA
- Venue
- 2025 IEEE International Conference on Data Mining Workshops (ICDMW)
- Publisher
- IEEE
- Published
- 2025-11-12
- Pages
- 1113-1117
- ISSN
- 2375-9259 (ISSN-L)
- OpenAlex
- W7134906349
- Cited by
- 0
- References
- 13
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE ... International Conference on Data Mining workshops (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Keywords
- semantic search, metadata filtering, e-commerce search, product attribute extraction, query decomposition, structured metadata, search result relevance, enterprise search
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
