{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/embedding-based-zero-shot-retrieval-through","title":"Embedding-based Zero-shot Retrieval through Query Generation","arxiv_id":"2009.10270","date":"2020-09-22","proceeding":null,"authors":["Davis Liang","Peng Xu","Siamak Shakeri","Cicero Nogueira dos Santos","Ramesh Nallapati","Zhiheng Huang","Bing Xiang"],"abstract":"Passage retrieval addresses the problem of locating relevant passages, usually from a large corpus, given a query. In practice, lexical term-matching algorithms like BM25 are popular choices for retrieval owing to their efficiency. However, term-based matching algorithms often miss relevant passages that have no lexical overlap with the query and cannot be finetuned to downstream datasets. In this work, we consider the embedding-based two-tower architecture as our neural retrieval model. Since labeled data can be scarce and because neural retrieval models require vast amounts of data to train, we propose a novel method for generating synthetic training data for retrieval. Our system produces remarkable results, significantly outperforming BM25 on 5 out of 6 datasets tested, by an average of 2.45 points for Recall@1. In some cases, our model trained on synthetic data can even outperform the same model trained on real data","url_abs":"https://arxiv.org/abs/2009.10270v1","url_pdf":"https://arxiv.org/pdf/2009.10270v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"embedding-based-zero-shot-retrieval-through","repo_url":"https://github.com/awslabs/neural-retrieval","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"passage-retrieval","task_name":"Passage Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.10270","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}