{"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/decoupling-strategy-and-generation-in","title":"Decoupling Strategy and Generation in Negotiation Dialogues","arxiv_id":"1808.09637","date":"2018-08-29","proceeding":"EMNLP 2018 10","authors":["He He","Derek Chen","Anusha Balakrishnan","Percy Liang"],"abstract":"We consider negotiation settings in which two agents use natural language to\nbargain on goods. Agents need to decide on both high-level strategy (e.g.,\nproposing \\$50) and the execution of that strategy (e.g., generating \"The bike\nis brand new. Selling for just \\$50.\"). Recent work on negotiation trains\nneural models, but their end-to-end nature makes it hard to control their\nstrategy, and reinforcement learning tends to lead to degenerate solutions. In\nthis paper, we propose a modular approach based on coarse di- alogue acts\n(e.g., propose(price=50)) that decouples strategy and generation. We show that\nwe can flexibly set the strategy using supervised learning, reinforcement\nlearning, or domain-specific knowledge without degeneracy, while our\nretrieval-based generation can maintain context-awareness and produce diverse\nutterances. We test our approach on the recently proposed DEALORNODEAL game,\nand we also collect a richer dataset based on real items on Craigslist. Human\nevaluation shows that our systems achieve higher task success rate and more\nhuman-like negotiation behavior than previous approaches.","url_abs":"http://arxiv.org/abs/1808.09637v1","url_pdf":"http://arxiv.org/pdf/1808.09637v1.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":"decoupling-strategy-and-generation-in","repo_url":"https://worksheets.codalab.org/worksheets/0x453913e76b65495d8b9730d41c7e0a0c","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"decoupling-strategy-and-generation-in","repo_url":"https://github.com/GeneralCoder365/agreemate","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"decoupling-strategy-and-generation-in","repo_url":"https://github.com/stanfordnlp/cocoa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[{"slug":"craigslistbargains","name":"CraigslistBargains","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.09637","atlas_url":"https://app.syntology.ai/?focus=1808.09637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.09637"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/GeneralCoder365/agreemate","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://worksheets.codalab.org/worksheets/0x453913e76b65495d8b9730d41c7e0a0c","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanfordnlp/cocoa","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":8},"by_repo_kind":{"listed":{"samples":9,"ran":1,"repositories":2}},"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":"051b6d3efcdab50c","entry":"random_multinomial","repo":"stanfordnlp/cocoa","repo_kind":"listed","path":"cocoa/core/util.py","file_url":"https://github.com/stanfordnlp/cocoa/blob/HEAD/cocoa/core/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"051b6d3efcdab50c"}},{"code_sha256_prefix":"ef864fbfa299918d","entry":"generate_symlink_mapping","repo":"GeneralCoder365/agreemate","repo_kind":"listed","path":"finetuning/symlink_mapper.py","file_url":"https://github.com/GeneralCoder365/agreemate/blob/HEAD/finetuning/symlink_mapper.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":"ef864fbfa299918d"}},{"code_sha256_prefix":"a55a15cdcc72d117","entry":"generate_uuid","repo":"stanfordnlp/cocoa","repo_kind":"listed","path":"cocoa/core/util.py","file_url":"https://github.com/stanfordnlp/cocoa/blob/HEAD/cocoa/core/util.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":"a55a15cdcc72d117"}},{"code_sha256_prefix":"79624785a930cf93","entry":"is_entity","repo":"stanfordnlp/cocoa","repo_kind":"listed","path":"cocoa/core/entity.py","file_url":"https://github.com/stanfordnlp/cocoa/blob/HEAD/cocoa/core/entity.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":"79624785a930cf93"}},{"code_sha256_prefix":"48ea52618655ff60","entry":"max_count","repo":"stanfordnlp/cocoa","repo_kind":"listed","path":"cocoa/lib/multi_bleu.py","file_url":"https://github.com/stanfordnlp/cocoa/blob/HEAD/cocoa/lib/multi_bleu.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":"48ea52618655ff60"}},{"code_sha256_prefix":"0f4b9388caba5928","entry":"min_count","repo":"stanfordnlp/cocoa","repo_kind":"listed","path":"cocoa/lib/multi_bleu.py","file_url":"https://github.com/stanfordnlp/cocoa/blob/HEAD/cocoa/lib/multi_bleu.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":"0f4b9388caba5928"}},{"code_sha256_prefix":"21919b592b94f529","entry":"ngram_count","repo":"stanfordnlp/cocoa","repo_kind":"listed","path":"cocoa/lib/multi_bleu.py","file_url":"https://github.com/stanfordnlp/cocoa/blob/HEAD/cocoa/lib/multi_bleu.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":"21919b592b94f529"}},{"code_sha256_prefix":"7cca4b0ef5f1ee30","entry":"setup_experiment_dir","repo":"GeneralCoder365/agreemate","repo_kind":"listed","path":"archive/baseline/run_experiments.py","file_url":"https://github.com/GeneralCoder365/agreemate/blob/HEAD/archive/baseline/run_experiments.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":"7cca4b0ef5f1ee30"}},{"code_sha256_prefix":"702b27974999a98a","entry":"tokenize","repo":"stanfordnlp/cocoa","repo_kind":"listed","path":"cocoa/core/tokenizer.py","file_url":"https://github.com/stanfordnlp/cocoa/blob/HEAD/cocoa/core/tokenizer.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":"702b27974999a98a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}