{"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/calibrate-your-listeners-robust-communication","title":"Calibrate your listeners! Robust communication-based training for pragmatic speakers","arxiv_id":"2110.05422","date":"2021-10-11","proceeding":"Findings (EMNLP) 2021 11","authors":["Rose E. Wang","Julia White","Jesse Mu","Noah D. Goodman"],"abstract":"To be good conversational partners, natural language processing (NLP) systems should be trained to produce contextually useful utterances. Prior work has investigated training NLP systems with communication-based objectives, where a neural listener stands in as a communication partner. However, these systems commonly suffer from semantic drift where the learned language diverges radically from natural language. We propose a method that uses a population of neural listeners to regularize speaker training. We first show that language drift originates from the poor uncertainty calibration of a neural listener, which makes high-certainty predictions on novel sentences. We explore ensemble- and dropout-based populations of listeners and find that the former results in better uncertainty quantification. We evaluate both population-based objectives on reference games, and show that the ensemble method with better calibration enables the speaker to generate pragmatic utterances while scaling to a large vocabulary and generalizing to new games and listeners.","url_abs":"https://arxiv.org/abs/2110.05422v1","url_pdf":"https://arxiv.org/pdf/2110.05422v1.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":"calibrate-your-listeners-robust-communication","repo_url":"https://github.com/rosewang2008/calibrate_your_listeners","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.05422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.05422"}},"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/rosewang2008/calibrate_your_listeners","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"7b22b006d4c675d1","entry":"Conv4","repo":"rosewang2008/calibrate_your_listeners","repo_kind":"official","path":"calibrate_your_listeners/src/models/vision.py","file_url":"https://github.com/rosewang2008/calibrate_your_listeners/blob/HEAD/calibrate_your_listeners/src/models/vision.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":"7b22b006d4c675d1"}},{"code_sha256_prefix":"be99f64faca5ddda","entry":"ResNet10","repo":"rosewang2008/calibrate_your_listeners","repo_kind":"official","path":"calibrate_your_listeners/src/models/vision.py","file_url":"https://github.com/rosewang2008/calibrate_your_listeners/blob/HEAD/calibrate_your_listeners/src/models/vision.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":"be99f64faca5ddda"}},{"code_sha256_prefix":"5c741ef76b8d640d","entry":"ResNet18","repo":"rosewang2008/calibrate_your_listeners","repo_kind":"official","path":"calibrate_your_listeners/src/models/vision.py","file_url":"https://github.com/rosewang2008/calibrate_your_listeners/blob/HEAD/calibrate_your_listeners/src/models/vision.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":"5c741ef76b8d640d"}},{"code_sha256_prefix":"ed3974fd95118700","entry":"load_raw_data","repo":"rosewang2008/calibrate_your_listeners","repo_kind":"official","path":"calibrate_your_listeners/src/datasets/shapeworld.py","file_url":"https://github.com/rosewang2008/calibrate_your_listeners/blob/HEAD/calibrate_your_listeners/src/datasets/shapeworld.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":"ed3974fd95118700"}},{"code_sha256_prefix":"e68f3fa02c6de0e8","entry":"to_onehot","repo":"rosewang2008/calibrate_your_listeners","repo_kind":"official","path":"calibrate_your_listeners/src/models/speaker.py","file_url":"https://github.com/rosewang2008/calibrate_your_listeners/blob/HEAD/calibrate_your_listeners/src/models/speaker.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":"e68f3fa02c6de0e8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}