{"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/directprobe-studying-representations-without","title":"DirectProbe: Studying Representations without Classifiers","arxiv_id":"2104.05904","date":"2021-04-13","proceeding":"NAACL 2021 4","authors":["Yichu Zhou","Vivek Srikumar"],"abstract":"Understanding how linguistic structures are encoded in contextualized embedding could help explain their impressive performance across NLP@. Existing approaches for probing them usually call for training classifiers and use the accuracy, mutual information, or complexity as a proxy for the representation's goodness. In this work, we argue that doing so can be unreliable because different representations may need different classifiers. We develop a heuristic, DirectProbe, that directly studies the geometry of a representation by building upon the notion of a version space for a task. Experiments with several linguistic tasks and contextualized embeddings show that, even without training classifiers, DirectProbe can shine light into how an embedding space represents labels, and also anticipate classifier performance for the representation.","url_abs":"https://arxiv.org/abs/2104.05904v1","url_pdf":"https://arxiv.org/pdf/2104.05904v1.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":"directprobe-studying-representations-without","repo_url":"https://github.com/utahnlp/DirectProbe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.05904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.05904"}},"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/utahnlp/DirectProbe","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":"5bcb43d32734848e","entry":"load_embeddings","repo":"utahnlp/DirectProbe","repo_kind":"official","path":"directprobe/utils.py","file_url":"https://github.com/utahnlp/DirectProbe/blob/HEAD/directprobe/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":"5bcb43d32734848e"}},{"code_sha256_prefix":"0bf6a6c82a967a6a","entry":"load_entities","repo":"utahnlp/DirectProbe","repo_kind":"official","path":"directprobe/utils.py","file_url":"https://github.com/utahnlp/DirectProbe/blob/HEAD/directprobe/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":"0bf6a6c82a967a6a"}},{"code_sha256_prefix":"d59d2007ad27229f","entry":"load_labels","repo":"utahnlp/DirectProbe","repo_kind":"official","path":"directprobe/utils.py","file_url":"https://github.com/utahnlp/DirectProbe/blob/HEAD/directprobe/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":"d59d2007ad27229f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}