{"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/finding-friends-and-flipping-frenemies","title":"Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory","arxiv_id":"2011.01856","date":"2020-11-03","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Hannah Chen","Yangfeng Ji","David Evans"],"abstract":"Most NLP datasets are manually labeled, so suffer from inconsistent labeling or limited size. We propose methods for automatically improving datasets by viewing them as graphs with expected semantic properties. We construct a paraphrase graph from the provided sentence pair labels, and create an augmented dataset by directly inferring labels from the original sentence pairs using a transitivity property. We use structural balance theory to identify likely mislabelings in the graph, and flip their labels. We evaluate our methods on paraphrase models trained using these datasets starting from a pretrained BERT model, and find that the automatically-enhanced training sets result in more accurate models.","url_abs":"https://arxiv.org/abs/2011.01856v1","url_pdf":"https://arxiv.org/pdf/2011.01856v1.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":"finding-friends-and-flipping-frenemies","repo_url":"https://github.com/hannahxchen/automatic-paraphrase-dataset-augmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"flip","method_name":"FLIP"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.01856","atlas_url":"https://app.syntology.ai/?focus=2011.01856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01856"}},"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/hannahxchen/automatic-paraphrase-dataset-augmentation","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/hannahxchen/automaticparaphrase-dataset-augmentation","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"eaf3fa88029b9cfb","entry":"generate_augmented","repo":"hannahxchen/automatic-paraphrase-dataset-augmentation","repo_kind":"official","path":"generate_qqp_datasets.py","file_url":"https://github.com/hannahxchen/automatic-paraphrase-dataset-augmentation/blob/HEAD/generate_qqp_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eaf3fa88029b9cfb"}},{"code_sha256_prefix":"740600e10c3a2d5d","entry":"infer_non_paraphrases","repo":"hannahxchen/automatic-paraphrase-dataset-augmentation","repo_kind":"official","path":"generate_qqp_datasets.py","file_url":"https://github.com/hannahxchen/automatic-paraphrase-dataset-augmentation/blob/HEAD/generate_qqp_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"740600e10c3a2d5d"}},{"code_sha256_prefix":"58f0ffdd54cb5c69","entry":"infer_transitive","repo":"hannahxchen/automatic-paraphrase-dataset-augmentation","repo_kind":"official","path":"generate_qqp_datasets.py","file_url":"https://github.com/hannahxchen/automatic-paraphrase-dataset-augmentation/blob/HEAD/generate_qqp_datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"58f0ffdd54cb5c69"}},{"code_sha256_prefix":"7b8770f6b596d35f","entry":"find_mislabeled_pairs","repo":"hannahxchen/automatic-paraphrase-dataset-augmentation","repo_kind":"official","path":"generate_qqp_datasets.py","file_url":"https://github.com/hannahxchen/automatic-paraphrase-dataset-augmentation/blob/HEAD/generate_qqp_datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7b8770f6b596d35f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}