{"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/interactive-machine-comprehension-with-1","title":"Interactive Machine Comprehension with Dynamic Knowledge Graphs","arxiv_id":"2109.00077","date":"2021-08-31","proceeding":"EMNLP 2021 11","authors":["Xingdi Yuan"],"abstract":"Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable. An agent must interact with an environment sequentially to gather necessary knowledge in order to answer a question. We hypothesize that graph representations are good inductive biases, which can serve as an agent's memory mechanism in iMRC tasks. We explore four different categories of graphs that can capture text information at various levels. We describe methods that dynamically build and update these graphs during information gathering, as well as neural models to encode graph representations in RL agents. Extensive experiments on iSQuAD suggest that graph representations can result in significant performance improvements for RL agents.","url_abs":"https://arxiv.org/abs/2109.00077v1","url_pdf":"https://arxiv.org/pdf/2109.00077v1.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":"interactive-machine-comprehension-with-1","repo_url":"https://github.com/xingdi-eric-yuan/imrc_graph_public","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.00077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00077"}},"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/xingdi-eric-yuan/imrc_graph_public","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":6,"samples":[{"code_sha256_prefix":"91eb0af694a5d554","entry":"compute_mask","repo":"xingdi-eric-yuan/imrc_graph_public","repo_kind":"official","path":"layers.py","file_url":"https://github.com/xingdi-eric-yuan/imrc_graph_public/blob/HEAD/layers.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91eb0af694a5d554"}},{"code_sha256_prefix":"908674347fcbfcd2","entry":"NegativeLogLoss","repo":"xingdi-eric-yuan/imrc_graph_public","repo_kind":"official","path":"layers.py","file_url":"https://github.com/xingdi-eric-yuan/imrc_graph_public/blob/HEAD/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":"908674347fcbfcd2"}},{"code_sha256_prefix":"bbcc29402ff4c0a5","entry":"evaluate_observation_infomax","repo":"xingdi-eric-yuan/imrc_graph_public","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/xingdi-eric-yuan/imrc_graph_public/blob/HEAD/evaluate.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":"bbcc29402ff4c0a5"}},{"code_sha256_prefix":"8949f561bba5107c","entry":"max_len","repo":"xingdi-eric-yuan/imrc_graph_public","repo_kind":"official","path":"generic.py","file_url":"https://github.com/xingdi-eric-yuan/imrc_graph_public/blob/HEAD/generic.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":"8949f561bba5107c"}},{"code_sha256_prefix":"499aa017b9e14605","entry":"to_np","repo":"xingdi-eric-yuan/imrc_graph_public","repo_kind":"official","path":"generic.py","file_url":"https://github.com/xingdi-eric-yuan/imrc_graph_public/blob/HEAD/generic.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":"499aa017b9e14605"}},{"code_sha256_prefix":"a22dcfef9da055e4","entry":"to_one_hot","repo":"xingdi-eric-yuan/imrc_graph_public","repo_kind":"official","path":"layers.py","file_url":"https://github.com/xingdi-eric-yuan/imrc_graph_public/blob/HEAD/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":"a22dcfef9da055e4"}},{"code_sha256_prefix":"f947fb149bc50f58","entry":"to_pt","repo":"xingdi-eric-yuan/imrc_graph_public","repo_kind":"official","path":"generic.py","file_url":"https://github.com/xingdi-eric-yuan/imrc_graph_public/blob/HEAD/generic.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":"f947fb149bc50f58"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}