{"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/distribution-matching-for-rationalization","title":"Distribution Matching for Rationalization","arxiv_id":"2106.00320","date":"2021-06-01","proceeding":null,"authors":["Yongfeng Huang","Yujun Chen","Yulun Du","Zhilin Yang"],"abstract":"The task of rationalization aims to extract pieces of input text as rationales to justify neural network predictions on text classification tasks. By definition, rationales represent key text pieces used for prediction and thus should have similar classification feature distribution compared to the original input text. However, previous methods mainly focused on maximizing the mutual information between rationales and labels while neglecting the relationship between rationales and input text. To address this issue, we propose a novel rationalization method that matches the distributions of rationales and input text in both the feature space and output space. Empirically, the proposed distribution matching approach consistently outperforms previous methods by a large margin. Our data and code are available.","url_abs":"https://arxiv.org/abs/2106.00320v1","url_pdf":"https://arxiv.org/pdf/2106.00320v1.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":"distribution-matching-for-rationalization","repo_url":"https://github.com/kochsnow/distribution-matching-rationality","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.00320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00320"}},"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/kochsnow/distribution-matching-rationality","reach":null}],"summary":{"ran":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":"fcb264218aac7183","entry":"Distance","repo":"kochsnow/distribution-matching-rationality","repo_kind":"official","path":"core/dist.py","file_url":"https://github.com/kochsnow/distribution-matching-rationality/blob/HEAD/core/dist.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fcb264218aac7183"}},{"code_sha256_prefix":"3c3a10a38d523302","entry":"l2diff","repo":"kochsnow/distribution-matching-rationality","repo_kind":"official","path":"core/dist.py","file_url":"https://github.com/kochsnow/distribution-matching-rationality/blob/HEAD/core/dist.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c3a10a38d523302"}},{"code_sha256_prefix":"554a1badcccb0448","entry":"gaussian_kernel","repo":"kochsnow/distribution-matching-rationality","repo_kind":"official","path":"core/dist.py","file_url":"https://github.com/kochsnow/distribution-matching-rationality/blob/HEAD/core/dist.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":"554a1badcccb0448"}},{"code_sha256_prefix":"afd328b898e67a0c","entry":"moment_diff","repo":"kochsnow/distribution-matching-rationality","repo_kind":"official","path":"core/dist.py","file_url":"https://github.com/kochsnow/distribution-matching-rationality/blob/HEAD/core/dist.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":"afd328b898e67a0c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}