{"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/opentag-open-attribute-value-extraction-from","title":"OpenTag: Open Attribute Value Extraction from Product Profiles [Deep Learning, Active Learning, Named Entity Recognition]","arxiv_id":"1806.01264","date":"2018-06-01","proceeding":null,"authors":["Guineng Zheng","Subhabrata Mukherjee","Xin Luna Dong","Fei-Fei Li"],"abstract":"Extraction of missing attribute values is to find values describing an\nattribute of interest from a free text input. Most past related work on\nextraction of missing attribute values work with a closed world assumption with\nthe possible set of values known beforehand, or use dictionaries of values and\nhand-crafted features. How can we discover new attribute values that we have\nnever seen before? Can we do this with limited human annotation or supervision?\nWe study this problem in the context of product catalogs that often have\nmissing values for many attributes of interest.\n  In this work, we leverage product profile information such as titles and\ndescriptions to discover missing values of product attributes. We develop a\nnovel deep tagging model OpenTag for this extraction problem with the following\ncontributions: (1) we formalize the problem as a sequence tagging task, and\npropose a joint model exploiting recurrent neural networks (specifically,\nbidirectional LSTM) to capture context and semantics, and Conditional Random\nFields (CRF) to enforce tagging consistency, (2) we develop a novel attention\nmechanism to provide interpretable explanation for our model's decisions, (3)\nwe propose a novel sampling strategy exploring active learning to reduce the\nburden of human annotation. OpenTag does not use any dictionary or hand-crafted\nfeatures as in prior works. Extensive experiments in real-life datasets in\ndifferent domains show that OpenTag with our active learning strategy discovers\nnew attribute values from as few as 150 annotated samples (reduction in 3.3x\namount of annotation effort) with a high F-score of 83%, outperforming\nstate-of-the-art models.","url_abs":"http://arxiv.org/abs/1806.01264v2","url_pdf":"http://arxiv.org/pdf/1806.01264v2.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":"opentag-open-attribute-value-extraction-from","repo_url":"https://github.com/hackerxiaobai/OpenTag_2019","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"opentag-open-attribute-value-extraction-from","repo_url":"https://github.com/lumiqai/UOI-1806.01264","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"attribute-value-extraction","task_name":"Attribute Value Extraction"},{"task_slug":"missing-values","task_name":"Missing Values"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.01264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.01264"}},"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/lumiqai/UOI-1806.01264","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hackerxiaobai/OpenTag_2019","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"e35fa5058b677cb0","entry":"X_padding","repo":"hackerxiaobai/OpenTag_2019","repo_kind":"listed","path":"utils/data_process.py","file_url":"https://github.com/hackerxiaobai/OpenTag_2019/blob/HEAD/utils/data_process.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e35fa5058b677cb0"}},{"code_sha256_prefix":"829c5c20f3fcf74d","entry":"bert4token","repo":"hackerxiaobai/OpenTag_2019","repo_kind":"listed","path":"utils/data_process.py","file_url":"https://github.com/hackerxiaobai/OpenTag_2019/blob/HEAD/utils/data_process.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":"829c5c20f3fcf74d"}},{"code_sha256_prefix":"27d7ddd56cb02db7","entry":"nobert4token","repo":"hackerxiaobai/OpenTag_2019","repo_kind":"listed","path":"utils/data_process.py","file_url":"https://github.com/hackerxiaobai/OpenTag_2019/blob/HEAD/utils/data_process.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":"27d7ddd56cb02db7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}