{"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/commonsense-for-generative-multi-hop-question","title":"Commonsense for Generative Multi-Hop Question Answering Tasks","arxiv_id":"1809.06309","date":"2018-09-17","proceeding":"EMNLP 2018 10","authors":["Lisa Bauer","Yicheng Wang","Mohit Bansal"],"abstract":"Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multi-hop generative task (NarrativeQA), which requires the model to reason, gather, and synthesize disjoint pieces of information within the context to generate an answer. This type of multi-step reasoning also often requires understanding implicit relations, which humans resolve via external, background commonsense knowledge. We first present a strong generative baseline that uses a multi-attention mechanism to perform multiple hops of reasoning and a pointer-generator decoder to synthesize the answer. This model performs substantially better than previous generative models, and is competitive with current state-of-the-art span prediction models. We next introduce a novel system for selecting grounded multi-hop relational commonsense information from ConceptNet via a pointwise mutual information and term-frequency based scoring function. Finally, we effectively use this extracted commonsense information to fill in gaps of reasoning between context hops, using a selectively-gated attention mechanism. This boosts the model's performance significantly (also verified via human evaluation), establishing a new state-of-the-art for the task. We also show promising initial results of the generalizability of our background knowledge enhancements by demonstrating some improvement on QAngaroo-WikiHop, another multi-hop reasoning dataset.","url_abs":"https://arxiv.org/abs/1809.06309v3","url_pdf":"https://arxiv.org/pdf/1809.06309v3.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":"commonsense-for-generative-multi-hop-question","repo_url":"https://github.com/yicheng-w/CommonSenseMultiHopQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"commonsense-for-generative-multi-hop-question","repo_url":"https://github.com/a414351664/NarrativeQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"implicit-relations","task_name":"Implicit Relations"},{"task_slug":"multi-hop-question-answering","task_name":"Multi-hop Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-narrativeqa","task":"Question Answering","dataset":"NarrativeQA","model":"MHPGM + NOIC","rank_in_archive_order":6,"of":10,"metrics":{"BLEU-1":"43.63","BLEU-4":"21.07","METEOR":"19.03","Rouge-L":"44.16"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-wikihop","task":"Question Answering","dataset":"WikiHop","model":"MHPGM + NOIC","rank_in_archive_order":8,"of":9,"metrics":{"Test":"57.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.06309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.06309"}},"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/a414351664/NarrativeQA","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yicheng-w/CommonSenseMultiHopQA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":5,"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":"767033d2a158e95e","entry":"encode_commonsense","repo":"a414351664/NarrativeQA","repo_kind":"listed","path":"src/data.py","file_url":"https://github.com/a414351664/NarrativeQA/blob/HEAD/src/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"767033d2a158e95e"}},{"code_sha256_prefix":"b1dc93ca4a785d10","entry":"encode_commonsense_paths","repo":"a414351664/NarrativeQA","repo_kind":"listed","path":"src/data.py","file_url":"https://github.com/a414351664/NarrativeQA/blob/HEAD/src/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1dc93ca4a785d10"}},{"code_sha256_prefix":"63e2c59c60ff8e0c","entry":"eval_multiple_choice_dataset","repo":"a414351664/NarrativeQA","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/a414351664/NarrativeQA/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63e2c59c60ff8e0c"}},{"code_sha256_prefix":"3ad3ac6b3b3eab24","entry":"gen_mc_preds","repo":"a414351664/NarrativeQA","repo_kind":"listed","path":"src/utils.py","file_url":"https://github.com/a414351664/NarrativeQA/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ad3ac6b3b3eab24"}},{"code_sha256_prefix":"7384690e07b3416d","entry":"get_stop_words","repo":"yicheng-w/CommonSenseMultiHopQA","repo_kind":"official","path":"src/read_data.py","file_url":"https://github.com/yicheng-w/CommonSenseMultiHopQA/blob/HEAD/src/read_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7384690e07b3416d"}},{"code_sha256_prefix":"e5b96a8cac6d3215","entry":"get_stop_words_1","repo":"yicheng-w/CommonSenseMultiHopQA","repo_kind":"official","path":"src/read_data.py","file_url":"https://github.com/yicheng-w/CommonSenseMultiHopQA/blob/HEAD/src/read_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e5b96a8cac6d3215"}},{"code_sha256_prefix":"f853c33debd7891f","entry":"restore_vocab","repo":"a414351664/NarrativeQA","repo_kind":"listed","path":"src/data.py","file_url":"https://github.com/a414351664/NarrativeQA/blob/HEAD/src/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f853c33debd7891f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}