{"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/regen-reinforcement-learning-for-text-and","title":"ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models","arxiv_id":"2108.12472","date":"2021-08-27","proceeding":"EMNLP 2021 11","authors":["Pierre L. Dognin","Inkit Padhi","Igor Melnyk","Payel Das"],"abstract":"Automatic construction of relevant Knowledge Bases (KBs) from text, and generation of semantically meaningful text from KBs are both long-standing goals in Machine Learning. In this paper, we present ReGen, a bidirectional generation of text and graph leveraging Reinforcement Learning (RL) to improve performance. Graph linearization enables us to re-frame both tasks as a sequence to sequence generation problem regardless of the generative direction, which in turn allows the use of Reinforcement Learning for sequence training where the model itself is employed as its own critic leading to Self-Critical Sequence Training (SCST). We present an extensive investigation demonstrating that the use of RL via SCST benefits graph and text generation on WebNLG+ 2020 and TekGen datasets. Our system provides state-of-the-art results on WebNLG+ 2020 by significantly improving upon published results from the WebNLG 2020+ Challenge for both text-to-graph and graph-to-text generation tasks.","url_abs":"https://arxiv.org/abs/2108.12472v1","url_pdf":"https://arxiv.org/pdf/2108.12472v1.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":"regen-reinforcement-learning-for-text-and","repo_url":"https://github.com/IBM/regen","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"joint-entity-and-relation-extraction","task_name":"Joint Entity and Relation Extraction"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"reinforce","method_name":"REINFORCE"},{"method_slug":"scst","method_name":"SCST"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-9","task":"Joint Entity and Relation Extraction","dataset":"TekGen","model":"ReGen-SCST","rank_in_archive_order":1,"of":2,"metrics":{"F1":"62.3"},"uses_additional_data":false},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-9","task":"Joint Entity and Relation Extraction","dataset":"TekGen","model":"ReGen-CE","rank_in_archive_order":2,"of":2,"metrics":{"F1":"61.9"},"uses_additional_data":false},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-8","task":"Joint Entity and Relation Extraction","dataset":"WebNLG 3.0","model":"ReGen (Ours) T2G.CE","rank_in_archive_order":1,"of":10,"metrics":{"F1":"72.3"},"uses_additional_data":false},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-8","task":"Joint Entity and Relation Extraction","dataset":"WebNLG 3.0","model":"ReGen (Ours) T2G.RL","rank_in_archive_order":4,"of":10,"metrics":{"F1":"72"},"uses_additional_data":false},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-8","task":"Joint Entity and Relation Extraction","dataset":"WebNLG 3.0","model":"Amazon AI (Shanghai) (guo-etal-2020-2)","rank_in_archive_order":5,"of":10,"metrics":{"F1":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/joint-entity-and-relation-extraction-on-8","task":"Joint Entity and Relation Extraction","dataset":"WebNLG 3.0","model":"bt5 (agarwal-etal-2020-machine)","rank_in_archive_order":7,"of":10,"metrics":{"F1":"68.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.12472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.12472"}},"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":"deterministic:regex_extraction","url":"https://github.com/IBM/regen","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"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":"4f1c685480732b74","entry":"check_and_add_arguments","repo":"IBM/regen","repo_kind":"official","path":"opts.py","file_url":"https://github.com/IBM/regen/blob/HEAD/opts.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":"4f1c685480732b74"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}