{"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/robust-distant-supervision-relation","title":"Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning","arxiv_id":"1805.09927","date":"2018-05-24","proceeding":"ACL 2018 7","authors":["Pengda Qin","Weiran Xu","William Yang Wang"],"abstract":"Distant supervision has become the standard method for relation extraction.\nHowever, even though it is an efficient method, it does not come at no\ncost---The resulted distantly-supervised training samples are often very noisy.\nTo combat the noise, most of the recent state-of-the-art approaches focus on\nselecting one-best sentence or calculating soft attention weights over the set\nof the sentences of one specific entity pair. However, these methods are\nsuboptimal, and the false positive problem is still a key stumbling bottleneck\nfor the performance. We argue that those incorrectly-labeled candidate\nsentences must be treated with a hard decision, rather than being dealt with\nsoft attention weights. To do this, our paper describes a radical solution---We\nexplore a deep reinforcement learning strategy to generate the false-positive\nindicator, where we automatically recognize false positives for each relation\ntype without any supervised information. Unlike the removal operation in the\nprevious studies, we redistribute them into the negative examples. The\nexperimental results show that the proposed strategy significantly improves the\nperformance of distant supervision comparing to state-of-the-art systems.","url_abs":"http://arxiv.org/abs/1805.09927v1","url_pdf":"http://arxiv.org/pdf/1805.09927v1.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":"robust-distant-supervision-relation","repo_url":"https://github.com/Panda0406/Adversarial-Learning-Distant-Supervision-RE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"robust-distant-supervision-relation","repo_url":"https://github.com/Panda0406/Reinforcement-Learning-Distant-Supervision-RE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.09927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09927"}},"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/Panda0406/Adversarial-Learning-Distant-Supervision-RE","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Panda0406/Reinforcement-Learning-Distant-Supervision-RE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"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":"81906c2f09ca9bd4","entry":"fix_params","repo":"Panda0406/Adversarial-Learning-Distant-Supervision-RE","repo_kind":"listed","path":"pretrain.py","file_url":"https://github.com/Panda0406/Adversarial-Learning-Distant-Supervision-RE/blob/HEAD/pretrain.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":"81906c2f09ca9bd4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}