{"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/multi-step-reasoning-over-unstructured-text","title":"Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval","arxiv_id":"2104.05883","date":"2021-04-13","proceeding":"NAACL 2021 4","authors":["Chen Zhao","Chenyan Xiong","Jordan Boyd-Graber","Hal Daumé III"],"abstract":"Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces. Current approaches incorporate the strengths of structured knowledge and unstructured text, assuming text corpora is semi-structured. Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. When evaluated on multi-hop question answering, BeamDR is competitive to state-of-the-art systems, without using any semi-structured information. Through query composition in dense space, BeamDR captures the implicit relationships between evidence in the reasoning chain. The code is available at https://github.com/ henryzhao5852/BeamDR.","url_abs":"https://arxiv.org/abs/2104.05883v1","url_pdf":"https://arxiv.org/pdf/2104.05883v1.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":"multi-step-reasoning-over-unstructured-text","repo_url":"https://github.com/henryzhao5852/BeamDR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-hop-question-answering","task_name":"Multi-hop Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.05883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05883"}},"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/henryzhao5852/BeamDR","reach":null}],"summary":{"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"961ebd963e5d10b1","entry":"EmbeddingMixin","repo":"henryzhao5852/BeamDR","repo_kind":"official","path":"beamdr/model/models.py","file_url":"https://github.com/henryzhao5852/BeamDR/blob/HEAD/beamdr/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"961ebd963e5d10b1"}},{"code_sha256_prefix":"5633be865f36a500","entry":"RobertaDot_CLF_ANN_NLL_MultiChunk","repo":"henryzhao5852/BeamDR","repo_kind":"official","path":"beamdr/model/models.py","file_url":"https://github.com/henryzhao5852/BeamDR/blob/HEAD/beamdr/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5633be865f36a500"}},{"code_sha256_prefix":"0c7de0ae2d4be25e","entry":"RobertaDot_NLL_LN","repo":"henryzhao5852/BeamDR","repo_kind":"official","path":"beamdr/model/models.py","file_url":"https://github.com/henryzhao5852/BeamDR/blob/HEAD/beamdr/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c7de0ae2d4be25e"}},{"code_sha256_prefix":"2c472fc3a0066112","entry":"NLL","repo":"henryzhao5852/BeamDR","repo_kind":"official","path":"beamdr/model/models.py","file_url":"https://github.com/henryzhao5852/BeamDR/blob/HEAD/beamdr/model/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c472fc3a0066112"}},{"code_sha256_prefix":"b57b113ad6f3dbe0","entry":"NLL_MultiChunk","repo":"henryzhao5852/BeamDR","repo_kind":"official","path":"beamdr/model/models.py","file_url":"https://github.com/henryzhao5852/BeamDR/blob/HEAD/beamdr/model/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b57b113ad6f3dbe0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}