{"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/mare-multi-aspect-rationale-extractor-on","title":"MARE: Multi-Aspect Rationale Extractor on Unsupervised Rationale Extraction","arxiv_id":"2410.03531","date":"2024-10-04","proceeding":null,"authors":["Han Jiang","Junwen Duan","Zhe Qu","Jianxin Wang"],"abstract":"Unsupervised rationale extraction aims to extract text snippets to support model predictions without explicit rationale annotation. Researchers have made many efforts to solve this task. Previous works often encode each aspect independently, which may limit their ability to capture meaningful internal correlations between aspects. While there has been significant work on mitigating spurious correlations, our approach focuses on leveraging the beneficial internal correlations to improve multi-aspect rationale extraction. In this paper, we propose a Multi-Aspect Rationale Extractor (MARE) to explain and predict multiple aspects simultaneously. Concretely, we propose a Multi-Aspect Multi-Head Attention (MAMHA) mechanism based on hard deletion to encode multiple text chunks simultaneously. Furthermore, multiple special tokens are prepended in front of the text with each corresponding to one certain aspect. Finally, multi-task training is deployed to reduce the training overhead. Experimental results on two unsupervised rationale extraction benchmarks show that MARE achieves state-of-the-art performance. Ablation studies further demonstrate the effectiveness of our method. Our codes have been available at https://github.com/CSU-NLP-Group/MARE.","url_abs":"https://arxiv.org/abs/2410.03531v1","url_pdf":"https://arxiv.org/pdf/2410.03531v1.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":[],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.03531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03531"}},"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":"deterministic:regex_extraction","url":"https://github.com/CSU-NLP-Group/MARE","reach":{"status":"ok"}}],"summary":{"ran":7,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":8,"ran":7,"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":8,"samples":[{"code_sha256_prefix":"5b66bd511e0a59b1","entry":"check","repo":"CSU-NLP-Group/MARE","repo_kind":"found_in_text","path":"src/run_classification.py","file_url":"https://github.com/CSU-NLP-Group/MARE/blob/HEAD/src/run_classification.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5b66bd511e0a59b1"}},{"code_sha256_prefix":"f69a4b908197ca42","entry":"convert_softmax_mask_to_digit","repo":"CSU-NLP-Group/MARE","repo_kind":"found_in_text","path":"src/module/modeling_utils.py","file_url":"https://github.com/CSU-NLP-Group/MARE/blob/HEAD/src/module/modeling_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f69a4b908197ca42"}},{"code_sha256_prefix":"4b3525873771df0d","entry":"get_certain_layer","repo":"CSU-NLP-Group/MARE","repo_kind":"found_in_text","path":"src/module/modeling_utils.py","file_url":"https://github.com/CSU-NLP-Group/MARE/blob/HEAD/src/module/modeling_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b3525873771df0d"}},{"code_sha256_prefix":"999e0ed53afc8282","entry":"get_mare_predictor","repo":"CSU-NLP-Group/MARE","repo_kind":"found_in_text","path":"src/module/modeling_mare_predictor.py","file_url":"https://github.com/CSU-NLP-Group/MARE/blob/HEAD/src/module/modeling_mare_predictor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"999e0ed53afc8282"}},{"code_sha256_prefix":"5c3302affb85090a","entry":"get_multiple_layer","repo":"CSU-NLP-Group/MARE","repo_kind":"found_in_text","path":"src/module/modeling_utils.py","file_url":"https://github.com/CSU-NLP-Group/MARE/blob/HEAD/src/module/modeling_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5c3302affb85090a"}},{"code_sha256_prefix":"3909f448f84543e1","entry":"is_eraser","repo":"CSU-NLP-Group/MARE","repo_kind":"found_in_text","path":"src/run_classification.py","file_url":"https://github.com/CSU-NLP-Group/MARE/blob/HEAD/src/run_classification.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3909f448f84543e1"}},{"code_sha256_prefix":"0c72c32ab74575ea","entry":"to_list","repo":"CSU-NLP-Group/MARE","repo_kind":"found_in_text","path":"src/run_classification.py","file_url":"https://github.com/CSU-NLP-Group/MARE/blob/HEAD/src/run_classification.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c72c32ab74575ea"}},{"code_sha256_prefix":"efbb0f3903b5f779","entry":"load_tf_weights_in_bert","repo":"CSU-NLP-Group/MARE","repo_kind":"found_in_text","path":"src/module/modeling_mare.py","file_url":"https://github.com/CSU-NLP-Group/MARE/blob/HEAD/src/module/modeling_mare.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":"efbb0f3903b5f779"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}