{"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/towards-prediction-explainability-through","title":"The Explanation Game: Towards Prediction Explainability through Sparse Communication","arxiv_id":"2004.13876","date":"2020-04-28","proceeding":"EMNLP (BlackboxNLP) 2020 11","authors":["Marcos V. Treviso","André F. T. Martins"],"abstract":"Explainability is a topic of growing importance in NLP. In this work, we provide a unified perspective of explainability as a communication problem between an explainer and a layperson about a classifier's decision. We use this framework to compare several prior approaches for extracting explanations, including gradient methods, representation erasure, and attention mechanisms, in terms of their communication success. In addition, we reinterpret these methods at the light of classical feature selection, and we use this as inspiration to propose new embedded methods for explainability, through the use of selective, sparse attention. Experiments in text classification, natural language entailment, and machine translation, using different configurations of explainers and laypeople (including both machines and humans), reveal an advantage of attention-based explainers over gradient and erasure methods. Furthermore, human evaluation experiments show promising results with post-hoc explainers trained to optimize communication success and faithfulness.","url_abs":"https://arxiv.org/abs/2004.13876v2","url_pdf":"https://arxiv.org/pdf/2004.13876v2.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":"towards-prediction-explainability-through","repo_url":"https://github.com/deep-spin/spec","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"feature-selection","task_name":"feature selection"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.13876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13876"}},"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/deep-spin/spec","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":"b41fb3b146fd928f","entry":"configure_output","repo":"deep-spin/spec","repo_kind":"official","path":"spec/config_utils.py","file_url":"https://github.com/deep-spin/spec/blob/HEAD/spec/config_utils.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":"b41fb3b146fd928f"}},{"code_sha256_prefix":"397ecbba2ed1ca4b","entry":"extract_prefixes","repo":"deep-spin/spec","repo_kind":"official","path":"spec/features.py","file_url":"https://github.com/deep-spin/spec/blob/HEAD/spec/features.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":"397ecbba2ed1ca4b"}},{"code_sha256_prefix":"a09e6fa95507b8c3","entry":"total_variance_distance","repo":"deep-spin/spec","repo_kind":"official","path":"spec/metrics.py","file_url":"https://github.com/deep-spin/spec/blob/HEAD/spec/metrics.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":"a09e6fa95507b8c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}