{"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/miner-improving-out-of-vocabulary-named-1","title":"MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective","arxiv_id":"2204.04391","date":"2022-04-09","proceeding":"ACL 2022 5","authors":["Xiao Wang","Shihan Dou","Limao Xiong","Yicheng Zou","Qi Zhang","Tao Gui","Liang Qiao","Zhanzhan Cheng","Xuanjing Huang"],"abstract":"NER model has achieved promising performance on standard NER benchmarks. However, recent studies show that previous approaches may over-rely on entity mention information, resulting in poor performance on out-of-vocabulary (OOV) entity recognition. In this work, we propose MINER, a novel NER learning framework, to remedy this issue from an information-theoretic perspective. The proposed approach contains two mutual information-based training objectives: i) generalizing information maximization, which enhances representation via deep understanding of context and entity surface forms; ii) superfluous information minimization, which discourages representation from rote memorizing entity names or exploiting biased cues in data. Experiments on various settings and datasets demonstrate that it achieves better performance in predicting OOV entities.","url_abs":"https://arxiv.org/abs/2204.04391v2","url_pdf":"https://arxiv.org/pdf/2204.04391v2.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":"miner-improving-out-of-vocabulary-named-1","repo_url":"https://github.com/beyonderxx/miner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"miner-improving-out-of-vocabulary-named-1","repo_url":"https://github.com/2023-MindSpore-4/Code16/tree/main/guitao/MINER-main","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"cg","task_name":"NER"},{"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":[{"leaderboard":"/sota/named-entity-recognition-ner-on-jnlpba","task":"Named Entity Recognition (NER)","dataset":"JNLPBA","model":"MINER","rank_in_archive_order":16,"of":17,"metrics":{"F1":"77.03"},"uses_additional_data":false},{"leaderboard":"/sota/named-entity-recognition-on-wnut-2017","task":"Named Entity Recognition (NER)","dataset":"WNUT 2017","model":"MINER","rank_in_archive_order":10,"of":23,"metrics":{"F1":"54.86"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.04391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.04391"}},"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/BeyonderXX/MINER","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"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":"152034b65ed72643","entry":"UpperBound","repo":"BeyonderXX/MINER","repo_kind":"official","path":"models/MI_estimators.py","file_url":"https://github.com/BeyonderXX/MINER/blob/HEAD/models/MI_estimators.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"152034b65ed72643"}},{"code_sha256_prefix":"02c103470c99a658","entry":"vCLUB","repo":"BeyonderXX/MINER","repo_kind":"official","path":"models/MI_estimators.py","file_url":"https://github.com/BeyonderXX/MINER/blob/HEAD/models/MI_estimators.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"02c103470c99a658"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}