mlsanityData to 14 Oct 2026

(Vector) Space is Not the Final Frontier: Product Search as Program Synthesis

arXiv 2304.11473 ↗First posted 22 Apr 2023cs.IR cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

As ecommerce continues growing, huge investments in ML and NLP for Information Retrieval are following. While the vector space model dominated retrieval modelling in product search - even as vectorization itself greatly changed with the advent of deep learning -, our position paper argues in a contrarian fashion that program synthesis provides significant advantages for many queries and a significant number of players in the market. We detail the industry significance of the proposed approach, sketch implementation details, and address common objections drawing from our experience building a similar system at Tooso.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 70 references that are in the map. First posted on arXiv 22 Apr 2023.

Builds on

29 of 70 references.

References · 29

  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  2. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  3. 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 372
  4. 2023Evaluating Verifiability in Generative Search Enginescited by 303
  5. 2022Transformer Memory as a Differentiable Search Indexcited by 247
  6. 2018Explainable Recommendation: A Survey and New Perspectivescited by 210
  7. 2019Multi-Stage Document Ranking with BERTcited by 201
  8. 2016Data Recombination for Neural Semantic Parsingcited by 111
  9. 2017Joint Extraction of Entities and Relations Based on a Novel Tagging Schemecited by 102
  10. 2022Compositional Semantic Parsing with Large Language Modelscited by 95
  11. 2020Word meaning in minds and machinescited by 51
  12. 2018End-to-End Retrieval in Continuous Spacecited by 46
17 more
  1. 2022Contrastive language and vision learning of general fashion conceptscited by 42
  2. 2021Improving Text-to-SQL with Schema Dependency Learningcited by 25
  3. 2022CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsingcited by 21
  4. 2020Fantastic Embeddings and How to Align Them: Zero-Shot Inference in a Multi-Shop Scenariocited by 16
  5. 2020Choppy: Cut Transformer For Ranked List Truncationcited by 11
  6. 2021SIGIR 2021 E-Commerce Workshop Data Challengecited by 11
  7. 2016Product Classification in E-Commerce using Distributional Semanticscited by 9
  8. 2021Model-agnostic vs. Model-intrinsic Interpretability for Explainable Product Searchcited by 7
  9. 2020How to Grow a (Product) Tree: Personalized Category Suggestions for eCommerce Type-Aheadcited by 6
  10. 2021Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interactioncited by 5
  11. 2021You Do Not Need a Bigger Boat: Recommendations at Reasonable Scale in a (Mostly) Serverless and Open Stackcited by 5
  12. 2023Reasonable Scale Machine Learning with Open-Source Metaflowcited by 5
  13. 2020"An Image is Worth a Thousand Features": Scalable Product Representations for In-Session Type-Ahead Personalizationcited by 4
  14. 2022"Does it come in black?" CLIP-like models are zero-shot recommenderscited by 4
  15. 2018End-to-End Neural Ranking for eCommerce Product Search: an application of task models and textual embeddingscited by 2
  16. 2021From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Searchcited by 2
  17. 2019Personalized Re-ranking for Recommendationcited by 1

Built on by

Not cited yet.