Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search
A new paper presents a robust neural sparse retrieval system aimed at improving music search efficiency. The system addresses challenges posed by user query variations and aims to enhance recall rates while maintaining low latency. Evaluations indicate significant performance improvements over traditional methods, particularly in handling long-tail queries.
- ▪The proposed system achieves a recall rate of 91.4% at the top 10 results, compared to 57.7% for traditional trigrams.
- ▪It utilizes a domain-specific granular subword tokenization strategy to enhance surface-form robustness.
- ▪The approach minimizes online processing to achieve effectively zero latency overhead for query encoding.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.17762 |
| Publication time | Tue, 19 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-19T04:04:57.272Z |
| Last seen | 2026-05-19T04:04:57.272Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | yT4pwO8uP-kN |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.17762 (cs) [Submitted on 18 May 2026] Title:Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search Authors:Paul Greyson, Zhichao Geng, Wei Zhang, Yang Yang View a PDF of the paper titled Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search, by Paul Greyson and 3 other authors View PDF HTML (experimental) Abstract:Music search at the scale of Amazon Music presents a unique challenge: queries frequently deviate from indexed metadata due to misspellings, transpositions, and phonetic variations, yet the retrieval system must operate under strict millisecond-level latency constraints.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
