{"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/document-expansion-by-query-prediction","title":"Document Expansion by Query Prediction","arxiv_id":"1904.08375","date":"2019-04-17","proceeding":null,"authors":["Rodrigo Nogueira","Wei Yang","Jimmy Lin","Kyunghyun Cho"],"abstract":"One technique to improve the retrieval effectiveness of a search engine is to expand documents with terms that are related or representative of the documents' content.From the perspective of a question answering system, this might comprise questions the document can potentially answer. Following this observation, we propose a simple method that predicts which queries will be issued for a given document and then expands it with those predictions with a vanilla sequence-to-sequence model, trained using datasets consisting of pairs of query and relevant documents. By combining our method with a highly-effective re-ranking component, we achieve the state of the art in two retrieval tasks. In a latency-critical regime, retrieval results alone (without re-ranking) approach the effectiveness of more computationally expensive neural re-rankers but are much faster.","url_abs":"https://arxiv.org/abs/1904.08375v2","url_pdf":"https://arxiv.org/pdf/1904.08375v2.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":"document-expansion-by-query-prediction","repo_url":"https://github.com/nyu-dl/dl4ir-doc2query","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"document-expansion-by-query-prediction","repo_url":"https://github.com/castorini/Anserini","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"document-expansion-by-query-prediction","repo_url":"https://github.com/castorini/docTTTTTquery","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"document-expansion-by-query-prediction","repo_url":"https://github.com/irgroup/clef2023-longeval-irc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"document-expansion-by-query-prediction","repo_url":"https://github.com/kasys-lab/anserini-kasys","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"passage-re-ranking","task_name":"Passage Re-Ranking"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/passage-re-ranking-on-ms-marco","task":"Passage Re-Ranking","dataset":"MS MARCO","model":"BERT + Doc2query","rank_in_archive_order":2,"of":4,"metrics":{"MRR":"0.368"},"uses_additional_data":false},{"leaderboard":"/sota/passage-re-ranking-on-trec-pm","task":"Passage Re-Ranking","dataset":"TREC-PM","model":"BERT + Doc2query","rank_in_archive_order":1,"of":1,"metrics":{"mAP":"36.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.08375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08375"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/castorini/Anserini","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/castorini/docTTTTTquery","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kasys-lab/anserini-kasys","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nyu-dl/dl4ir-doc2query","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/irgroup/clef2023-longeval-irc","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a301adb26733f6c6","entry":"load_collection","repo":"nyu-dl/dl4ir-doc2query","repo_kind":"official","path":"convert_msmarco_to_opennmt.py","file_url":"https://github.com/nyu-dl/dl4ir-doc2query/blob/HEAD/convert_msmarco_to_opennmt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a301adb26733f6c6"}},{"code_sha256_prefix":"43fa12d3c9abf09c","entry":"load_qrels","repo":"nyu-dl/dl4ir-doc2query","repo_kind":"official","path":"convert_msmarco_to_opennmt.py","file_url":"https://github.com/nyu-dl/dl4ir-doc2query/blob/HEAD/convert_msmarco_to_opennmt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"43fa12d3c9abf09c"}},{"code_sha256_prefix":"1b008cef2a2994db","entry":"load_queries","repo":"nyu-dl/dl4ir-doc2query","repo_kind":"official","path":"convert_msmarco_to_opennmt.py","file_url":"https://github.com/nyu-dl/dl4ir-doc2query/blob/HEAD/convert_msmarco_to_opennmt.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1b008cef2a2994db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}