{"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/merit-meta-path-guided-contrastive-learning","title":"MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning","arxiv_id":"2203.00357","date":"2022-03-01","proceeding":"Findings (ACL) 2022 5","authors":["Fangkai Jiao","Yangyang Guo","Xuemeng Song","Liqiang Nie"],"abstract":"Logical reasoning is of vital importance to natural language understanding. Previous studies either employ graph-based models to incorporate prior knowledge about logical relations, or introduce symbolic logic into neural models through data augmentation. These methods, however, heavily depend on annotated training data, and thus suffer from over-fitting and poor generalization problems due to the dataset sparsity. To address these two problems, in this paper, we propose MERIt, a MEta-path guided contrastive learning method for logical ReasonIng of text, to perform self-supervised pre-training on abundant unlabeled text data. Two novel strategies serve as indispensable components of our method. In particular, a strategy based on meta-path is devised to discover the logical structure in natural texts, followed by a counterfactual data augmentation strategy to eliminate the information shortcut induced by pre-training. The experimental results on two challenging logical reasoning benchmarks, i.e., ReClor and LogiQA, demonstrate that our method outperforms the SOTA baselines with significant improvements.","url_abs":"https://arxiv.org/abs/2203.00357v1","url_pdf":"https://arxiv.org/pdf/2203.00357v1.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":"merit-meta-path-guided-contrastive-learning","repo_url":"https://github.com/sparkjiao/merit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/reading-comprehension-on-reclor","task":"Reading Comprehension","dataset":"ReClor","model":"MERIt(MERIt-deberta-v2-xxlarge )","rank_in_archive_order":3,"of":39,"metrics":{"Test":"79.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.00357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.00357"}},"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/sparkjiao/merit","reach":null}],"summary":{"ran":2,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"bae3f62db60db88a","entry":"AverageMeter","repo":"sparkjiao/merit","repo_kind":"official","path":"models/roberta_sent_att_sup.py","file_url":"https://github.com/sparkjiao/merit/blob/HEAD/models/roberta_sent_att_sup.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bae3f62db60db88a"}},{"code_sha256_prefix":"6a70f455b6a0d63e","entry":"LogMixin","repo":"sparkjiao/merit","repo_kind":"official","path":"models/roberta_sent_att_sup.py","file_url":"https://github.com/sparkjiao/merit/blob/HEAD/models/roberta_sent_att_sup.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a70f455b6a0d63e"}},{"code_sha256_prefix":"b90c2f73ba830814","entry":"extract_sent_tokens","repo":"sparkjiao/merit","repo_kind":"official","path":"models/roberta_sent_att_sup.py","file_url":"https://github.com/sparkjiao/merit/blob/HEAD/models/roberta_sent_att_sup.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b90c2f73ba830814"}},{"code_sha256_prefix":"15b69fa520a0583e","entry":"get_accuracy","repo":"sparkjiao/merit","repo_kind":"official","path":"models/roberta_sent_att_sup.py","file_url":"https://github.com/sparkjiao/merit/blob/HEAD/models/roberta_sent_att_sup.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"15b69fa520a0583e"}},{"code_sha256_prefix":"477a33ae801770b3","entry":"get_child_logger","repo":"sparkjiao/merit","repo_kind":"official","path":"models/roberta_sent_att_sup.py","file_url":"https://github.com/sparkjiao/merit/blob/HEAD/models/roberta_sent_att_sup.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"477a33ae801770b3"}},{"code_sha256_prefix":"490e26c4efc3d75f","entry":"LogMetric","repo":"sparkjiao/merit","repo_kind":"official","path":"models/roberta_sent_att_sup.py","file_url":"https://github.com/sparkjiao/merit/blob/HEAD/models/roberta_sent_att_sup.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"490e26c4efc3d75f"}},{"code_sha256_prefix":"f81e954124a605c1","entry":"RobertaSentForMultipleChoice","repo":"sparkjiao/merit","repo_kind":"official","path":"models/roberta_sent_att_sup.py","file_url":"https://github.com/sparkjiao/merit/blob/HEAD/models/roberta_sent_att_sup.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f81e954124a605c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}