{"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/hierarchical-graph-network-for-multi-hop","title":"Hierarchical Graph Network for Multi-hop Question Answering","arxiv_id":"1911.03631","date":"2019-11-09","proceeding":"EMNLP 2020 11","authors":["Yuwei Fang","Siqi Sun","Zhe Gan","Rohit Pillai","Shuohang Wang","Jingjing Liu"],"abstract":"In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical graph is created by constructing nodes on different levels of granularity (questions, paragraphs, sentences, entities), the representations of which are initialized with pre-trained contextual encoders. Given this hierarchical graph, the initial node representations are updated through graph propagation, and multi-hop reasoning is performed via traversing through the graph edges for each subsequent sub-task (e.g., paragraph selection, supporting facts extraction, answer prediction). By weaving heterogeneous nodes into an integral unified graph, this hierarchical differentiation of node granularity enables HGN to support different question answering sub-tasks simultaneously. Experiments on the HotpotQA benchmark demonstrate that the proposed model achieves new state of the art, outperforming existing multi-hop QA approaches.","url_abs":"https://arxiv.org/abs/1911.03631v4","url_pdf":"https://arxiv.org/pdf/1911.03631v4.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":"hierarchical-graph-network-for-multi-hop","repo_url":"https://github.com/yuwfan/HGN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-hop-question-answering","task_name":"Multi-hop Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-hotpotqa","task":"Question Answering","dataset":"HotpotQA","model":"HGN + SemanticRetrievalMRS IR","rank_in_archive_order":32,"of":72,"metrics":{"ANS-EM":"0.567","ANS-F1":"0.692","JOINT-EM":"0.356","JOINT-F1":"0.599","SUP-EM":"0.500","SUP-F1":"0.764"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1911.03631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03631"}},"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/yuwfan/HGN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_violates":1,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":"211753ba29188d4e","entry":"gelu","repo":"yuwfan/HGN","repo_kind":"official","path":"transformers/modeling_bert.py","file_url":"https://github.com/yuwfan/HGN/blob/HEAD/transformers/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"code_sha256_prefix":"77601724cad03f95","entry":"gelu_new","repo":"yuwfan/HGN","repo_kind":"official","path":"transformers/modeling_bert.py","file_url":"https://github.com/yuwfan/HGN/blob/HEAD/transformers/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"77601724cad03f95"}},{"code_sha256_prefix":"567eab7347ce0c60","entry":"mean_pooling","repo":"yuwfan/HGN","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/yuwfan/HGN/blob/HEAD/models/layers.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"567eab7347ce0c60"}},{"code_sha256_prefix":"4f56c9a37e92815f","entry":"load_tf_weights_in_albert","repo":"yuwfan/HGN","repo_kind":"official","path":"transformers/modeling_albert.py","file_url":"https://github.com/yuwfan/HGN/blob/HEAD/transformers/modeling_albert.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":false,"mcp_get_code":{"code_sha256":"4f56c9a37e92815f"}},{"code_sha256_prefix":"ca4a7d28d683cd33","entry":"load_tf_weights_in_bert","repo":"yuwfan/HGN","repo_kind":"official","path":"transformers/modeling_bert.py","file_url":"https://github.com/yuwfan/HGN/blob/HEAD/transformers/modeling_bert.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":false,"mcp_get_code":{"code_sha256":"ca4a7d28d683cd33"}},{"code_sha256_prefix":"566a814700763aa8","entry":"tok_to_ent","repo":"yuwfan/HGN","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/yuwfan/HGN/blob/HEAD/models/layers.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":false,"mcp_get_code":{"code_sha256":"566a814700763aa8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}