{"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/spectra-sparse-structured-text","title":"SPECTRA: Sparse Structured Text Rationalization","arxiv_id":"2109.04552","date":"2021-09-09","proceeding":"EMNLP 2021 11","authors":["Nuno Miguel Guerreiro","André F. T. Martins"],"abstract":"Selective rationalization aims to produce decisions along with rationales (e.g., text highlights or word alignments between two sentences). Commonly, rationales are modeled as stochastic binary masks, requiring sampling-based gradient estimators, which complicates training and requires careful hyperparameter tuning. Sparse attention mechanisms are a deterministic alternative, but they lack a way to regularize the rationale extraction (e.g., to control the sparsity of a text highlight or the number of alignments). In this paper, we present a unified framework for deterministic extraction of structured explanations via constrained inference on a factor graph, forming a differentiable layer. Our approach greatly eases training and rationale regularization, generally outperforming previous work on what comes to performance and plausibility of the extracted rationales. We further provide a comparative study of stochastic and deterministic methods for rationale extraction for classification and natural language inference tasks, jointly assessing their predictive power, quality of the explanations, and model variability.","url_abs":"https://arxiv.org/abs/2109.04552v1","url_pdf":"https://arxiv.org/pdf/2109.04552v1.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":"spectra-sparse-structured-text","repo_url":"https://github.com/deep-spin/spectra-rationalization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"spectra-sparse-structured-text","repo_url":"https://github.com/princeton-nlp/rationale-robustness","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.04552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04552"}},"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/princeton-nlp/rationale-robustness","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deep-spin/spectra-rationalization","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"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":"0ccd640711c998a9","entry":"build_optimizer","repo":"deep-spin/spectra-rationalization","repo_kind":"official","path":"rationalizers/builders.py","file_url":"https://github.com/deep-spin/spectra-rationalization/blob/HEAD/rationalizers/builders.py","link_basis":"harvester_set","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":"0ccd640711c998a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}