# Beyond Lexical: A Semantic Retrieval Framework for Textual SearchEngine

arXiv: https://arxiv.org/abs/2008.03917 · HTML: https://mlsanity.com/paper/2008.03917/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2020.

## Built on by (most cited first, 1 of 1)

- [AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys](https://mlsanity.com/paper/2510.26012/) (2025)

## Abstract (arXiv)

Search engine has become a fundamental component in various web and mobile applications. Retrieving relevant documents from the massive datasets is challenging for a search engine system, especially when faced with verbose or tail queries. In this paper, we explore a vector space search framework for document retrieval. Specifically, we trained a deep semantic matching model so that each query and document can be encoded as a low dimensional embedding. Our model was trained based on BERT architecture. We deployed a fast k-nearest-neighbor index service for online serving. Both offline and online metrics demonstrate that our method improved retrieval performance and search quality considerably, particularly for tail