# Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search

arXiv: https://arxiv.org/abs/2605.17762 · HTML: https://mlsanity.com/paper/2605.17762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective](https://mlsanity.com/paper/2205.04733/) (2022)
- [CharacterBERT: Reconciling ELMo and BERT for Word-Level Open-Vocabulary Representations From Characters](https://mlsanity.com/paper/2010.10392/) (2020)
- [SPLADE-v3: New baselines for SPLADE](https://mlsanity.com/paper/2403.06789/) (2024)
- [Minimizing FLOPs to Learn Efficient Sparse Representations](https://mlsanity.com/paper/2004.05665/) (2020)
- [Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers](https://mlsanity.com/paper/2411.04403/) (2024)
- [Effective Inference-Free Retrieval for Learned Sparse Representations](https://mlsanity.com/paper/2505.01452/) (2025)

## Abstract (arXiv)

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. Our existing learning-to-retrieve system, the High Confidence Index (HCI), learns query-entity associations from customer behavior, relying on continual ``exploration'' to choose candidates. Traditional n-gram matching enables this exploration but suffers from poor semantic robustness and high noise, limiting the system's ability to learn from long-tail queries. In this work, we present a robust neural sparse retrieval system designed to maximize exploration efficiency. We adapt a state-of-the-art inference-free sparse retrieval architecture to the music domain, combining it with an effective domain-specific granular subword tokenization strategy. Our approach utilizes short-length token constraints (max 3 chars) to enforce the learning of surface-form robustness over lexical memorization. By pre-computing the neural embeddings and term expansions during the offline indexing phase, online processing is reduced to minimal tokenization and IDF weighting, achieving effectively zero latency overhead for query encoding. Evaluations on a 6M-document production corpus show an aggregate 91.4% recall@10 (vs. 57.7% for trigrams) at comparable throughput. Simulation of the HCI feedback loop demonstrates improved exploration efficiency, with +0.8% higher stabilized recall than production trigrams. Ablation studies indicate that our sparse training methodology drives the performance gains, while domain-specific pretraining provides a cost-effective alternative to large-scale general-purpose pretraining.