{"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/191013294","title":"Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control","arxiv_id":"1910.13294","date":"2019-10-29","proceeding":"IJCNLP 2019 11","authors":["Mo Yu","Shiyu Chang","Yang Zhang","Tommi S. Jaakkola"],"abstract":"Selective rationalization has become a common mechanism to ensure that predictive models reveal how they use any available features. The selection may be soft or hard, and identifies a subset of input features relevant for prediction. The setup can be viewed as a co-operate game between the selector (aka rationale generator) and the predictor making use of only the selected features. The co-operative setting may, however, be compromised for two reasons. First, the generator typically has no direct access to the outcome it aims to justify, resulting in poor performance. Second, there's typically no control exerted on the information left outside the selection. We revise the overall co-operative framework to address these challenges. We introduce an introspective model which explicitly predicts and incorporates the outcome into the selection process. Moreover, we explicitly control the rationale complement via an adversary so as not to leave any useful information out of the selection. We show that the two complementary mechanisms maintain both high predictive accuracy and lead to comprehensive rationales.","url_abs":"https://arxiv.org/abs/1910.13294v2","url_pdf":"https://arxiv.org/pdf/1910.13294v2.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":"191013294","repo_url":"https://github.com/Gorov/three_player_for_emnlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"191013294","repo_url":"https://github.com/tomdyer10/wine_expert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.13294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.13294"}},"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/Gorov/three_player_for_emnlp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tomdyer10/wine_expert","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"f67bc3dce6971638","entry":"count_regularization_baos_for_both","repo":"Gorov/three_player_for_emnlp","repo_kind":"official","path":"three_player_games/rationale_3players_for_emnlp.py","file_url":"https://github.com/Gorov/three_player_for_emnlp/blob/HEAD/three_player_games/rationale_3players_for_emnlp.py","link_basis":"first_harvest_node","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":"f67bc3dce6971638"}},{"code_sha256_prefix":"c1b1c048987ed618","entry":"create_relative_pos_embed_layer","repo":"Gorov/three_player_for_emnlp","repo_kind":"official","path":"three_player_games/rationale_3players_relation_classification_models.py","file_url":"https://github.com/Gorov/three_player_for_emnlp/blob/HEAD/three_player_games/rationale_3players_relation_classification_models.py","link_basis":"first_harvest_node","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":"c1b1c048987ed618"}},{"code_sha256_prefix":"7edb887a63e98aee","entry":"single_soft_regularization_loss","repo":"Gorov/three_player_for_emnlp","repo_kind":"official","path":"models/generator.py","file_url":"https://github.com/Gorov/three_player_for_emnlp/blob/HEAD/models/generator.py","link_basis":"first_harvest_node","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":"7edb887a63e98aee"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}