{"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/mphayaner-named-entity-recognition-for","title":"MphayaNER: Named Entity Recognition for Tshivenda","arxiv_id":"2304.03952","date":"2023-04-08","proceeding":null,"authors":["Rendani Mbuvha","David I. Adelani","Tendani Mutavhatsindi","Tshimangadzo Rakhuhu","Aluwani Mauda","Tshifhiwa Joshua Maumela","Andisani Masindi","Seani Rananga","Vukosi Marivate","Tshilidzi Marwala"],"abstract":"Named Entity Recognition (NER) plays a vital role in various Natural Language Processing tasks such as information retrieval, text classification, and question answering. However, NER can be challenging, especially in low-resource languages with limited annotated datasets and tools. This paper adds to the effort of addressing these challenges by introducing MphayaNER, the first Tshivenda NER corpus in the news domain. We establish NER baselines by \\textit{fine-tuning} state-of-the-art models on MphayaNER. The study also explores zero-shot transfer between Tshivenda and other related Bantu languages, with chiShona and Kiswahili showing the best results. Augmenting MphayaNER with chiShona data was also found to improve model performance significantly. Both MphayaNER and the baseline models are made publicly available.","url_abs":"https://arxiv.org/abs/2304.03952v1","url_pdf":"https://arxiv.org/pdf/2304.03952v1.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":"mphayaner-named-entity-recognition-for","repo_url":"https://github.com/rendanim/mphayaner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"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":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.03952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03952"}},"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/rendanim/mphayaner","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"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":0,"samples":[{"code_sha256_prefix":"366bf9d9c1ffe01e","entry":"convert_examples_to_features","repo":"rendanim/mphayaner","repo_kind":"official","path":"utils_ner.py","file_url":"https://github.com/rendanim/mphayaner/blob/HEAD/utils_ner.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"366bf9d9c1ffe01e"}},{"code_sha256_prefix":"c80e5c9a8ef905bf","entry":"read_examples_from_file","repo":"rendanim/mphayaner","repo_kind":"official","path":"utils_ner.py","file_url":"https://github.com/rendanim/mphayaner/blob/HEAD/utils_ner.py","link_basis":"harvester_set","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":"c80e5c9a8ef905bf"}},{"code_sha256_prefix":"cad5b48757653160","entry":"read_examples_from_file_flexible","repo":"rendanim/mphayaner","repo_kind":"official","path":"utils_ner.py","file_url":"https://github.com/rendanim/mphayaner/blob/HEAD/utils_ner.py","link_basis":"harvester_set","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":"cad5b48757653160"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}