{"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/reasoning-about-actions-and-state-changes-by","title":"Reasoning about Actions and State Changes by Injecting Commonsense Knowledge","arxiv_id":"1808.10012","date":"2018-08-29","proceeding":"EMNLP 2018 10","authors":["Niket Tandon","Bhavana Dalvi Mishra","Joel Grus","Wen-tau Yih","Antoine Bosselut","Peter Clark"],"abstract":"Comprehending procedural text, e.g., a paragraph describing photosynthesis,\nrequires modeling actions and the state changes they produce, so that questions\nabout entities at different timepoints can be answered. Although several recent\nsystems have shown impressive progress in this task, their predictions can be\nglobally inconsistent or highly improbable. In this paper, we show how the\npredicted effects of actions in the context of a paragraph can be improved in\ntwo ways: (1) by incorporating global, commonsense constraints (e.g., a\nnon-existent entity cannot be destroyed), and (2) by biasing reading with\npreferences from large-scale corpora (e.g., trees rarely move). Unlike earlier\nmethods, we treat the problem as a neural structured prediction task, allowing\nhard and soft constraints to steer the model away from unlikely predictions. We\nshow that the new model significantly outperforms earlier systems on a\nbenchmark dataset for procedural text comprehension (+8% relative gain), and\nthat it also avoids some of the nonsensical predictions that earlier systems\nmake.","url_abs":"http://arxiv.org/abs/1808.10012v1","url_pdf":"http://arxiv.org/pdf/1808.10012v1.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":"reasoning-about-actions-and-state-changes-by","repo_url":"https://github.com/allenai/propara","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.10012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.10012"}},"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/allenai/propara","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":"460309f614a4b60c","entry":"get_para","repo":"allenai/propara","repo_kind":"official","path":"propara/commonsense/model_output_loader.py","file_url":"https://github.com/allenai/propara/blob/HEAD/propara/commonsense/model_output_loader.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":"460309f614a4b60c"}},{"code_sha256_prefix":"0b6875756e243275","entry":"preprocess_locations","repo":"allenai/propara","repo_kind":"official","path":"propara/evaluation/evalQA.py","file_url":"https://github.com/allenai/propara/blob/HEAD/propara/evaluation/evalQA.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":"0b6875756e243275"}},{"code_sha256_prefix":"40df6681d7d3a7b1","entry":"step_id_at_pos","repo":"allenai/propara","repo_kind":"official","path":"propara/commonsense/model_output_loader.py","file_url":"https://github.com/allenai/propara/blob/HEAD/propara/commonsense/model_output_loader.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":"40df6681d7d3a7b1"}},{"code_sha256_prefix":"87da4864a1fa9599","entry":"step_ids","repo":"allenai/propara","repo_kind":"official","path":"propara/commonsense/model_output_loader.py","file_url":"https://github.com/allenai/propara/blob/HEAD/propara/commonsense/model_output_loader.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":"87da4864a1fa9599"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}