{"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/multidoc2dial-modeling-dialogues-grounded-in","title":"MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents","arxiv_id":"2109.12595","date":"2021-09-26","proceeding":"EMNLP 2021 11","authors":["Song Feng","Siva Sankalp Patel","Hui Wan","Sachindra Joshi"],"abstract":"We propose MultiDoc2Dial, a new task and dataset on modeling goal-oriented dialogues grounded in multiple documents. Most previous works treat document-grounded dialogue modeling as a machine reading comprehension task based on a single given document or passage. In this work, we aim to address more realistic scenarios where a goal-oriented information-seeking conversation involves multiple topics, and hence is grounded on different documents. To facilitate such a task, we introduce a new dataset that contains dialogues grounded in multiple documents from four different domains. We also explore modeling the dialogue-based and document-based context in the dataset. We present strong baseline approaches and various experimental results, aiming to support further research efforts on such a task.","url_abs":"https://arxiv.org/abs/2109.12595v1","url_pdf":"https://arxiv.org/pdf/2109.12595v1.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":"multidoc2dial-modeling-dialogues-grounded-in","repo_url":"https://github.com/IBM/multidoc2dial","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[{"slug":"multidoc2dial","name":"MultiDoc2Dial","full_name":"MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.12595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12595"}},"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/IBM/multidoc2dial","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"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":"46db9d78be46a32a","entry":"encode_line","repo":"IBM/multidoc2dial","repo_kind":"official","path":"dialdoc/utils/utils_rag.py","file_url":"https://github.com/IBM/multidoc2dial/blob/HEAD/dialdoc/utils/utils_rag.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"46db9d78be46a32a"}},{"code_sha256_prefix":"e46e521e38a3b168","entry":"get_top_n_indices","repo":"IBM/multidoc2dial","repo_kind":"official","path":"dialdoc/models/rag/retrieval_rag_dialdoc.py","file_url":"https://github.com/IBM/multidoc2dial/blob/HEAD/dialdoc/models/rag/retrieval_rag_dialdoc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e46e521e38a3b168"}},{"code_sha256_prefix":"123e0318bdbc48cb","entry":"load_bm25","repo":"IBM/multidoc2dial","repo_kind":"official","path":"dialdoc/utils/utils_rag.py","file_url":"https://github.com/IBM/multidoc2dial/blob/HEAD/dialdoc/utils/utils_rag.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"123e0318bdbc48cb"}},{"code_sha256_prefix":"d781c0319fd105f2","entry":"load_bm25_results","repo":"IBM/multidoc2dial","repo_kind":"official","path":"dialdoc/utils/utils_rag.py","file_url":"https://github.com/IBM/multidoc2dial/blob/HEAD/dialdoc/utils/utils_rag.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d781c0319fd105f2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}