{"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/afrihg-news-headline-generation-for-african","title":"AfriHG: News headline generation for African Languages","arxiv_id":"2412.20223","date":"2024-12-28","proceeding":null,"authors":["Toyib Ogunremi","Serah Akojenu","Anthony Soronnadi","Olubayo Adekanmbi","David Ifeoluwa Adelani"],"abstract":"This paper introduces AfriHG -- a news headline generation dataset created by combining from XLSum and MasakhaNEWS datasets focusing on 16 languages widely spoken by Africa. We experimented with two seq2eq models (mT5-base and AfriTeVa V2), and Aya-101 LLM. Our results show that Africa-centric seq2seq models such as AfriTeVa V2 outperform the massively multilingual mT5-base model. Finally, we show that the performance of fine-tuning AfriTeVa V2 with 313M parameters is competitive to prompting Aya-101 LLM with more than 13B parameters.","url_abs":"https://arxiv.org/abs/2412.20223v1","url_pdf":"https://arxiv.org/pdf/2412.20223v1.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":"afrihg-news-headline-generation-for-african","repo_url":"https://github.com/dadelani/AfriHG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"headline-generation","task_name":"Headline Generation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.20223","atlas_url":"https://app.syntology.ai/?focus=2412.20223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20223"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/dadelani/AfriHG","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"cf9ffa02a42184af","entry":"whitespace_tokenize","repo":"dadelani/AfriHG","repo_kind":"official","path":"Multi-Lang-Rouge/tokenizers.py","file_url":"https://github.com/dadelani/AfriHG/blob/HEAD/Multi-Lang-Rouge/tokenizers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf9ffa02a42184af"}},{"code_sha256_prefix":"1923fc05163d207d","entry":"convert_to_unicode","repo":"dadelani/AfriHG","repo_kind":"official","path":"Multi-Lang-Rouge/tokenizers.py","file_url":"https://github.com/dadelani/AfriHG/blob/HEAD/Multi-Lang-Rouge/tokenizers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"code_sha256_prefix":"fcc86dec3de74c55","entry":"fmeasure","repo":"dadelani/AfriHG","repo_kind":"official","path":"Multi-Lang-Rouge/scoring.py","file_url":"https://github.com/dadelani/AfriHG/blob/HEAD/Multi-Lang-Rouge/scoring.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fcc86dec3de74c55"}},{"code_sha256_prefix":"781e6a5a2f6282f9","entry":"lcs_ind","repo":"dadelani/AfriHG","repo_kind":"official","path":"Multi-Lang-Rouge/rouge_scorer.py","file_url":"https://github.com/dadelani/AfriHG/blob/HEAD/Multi-Lang-Rouge/rouge_scorer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"781e6a5a2f6282f9"}},{"code_sha256_prefix":"0e5615f8994003cf","entry":"printable_text","repo":"dadelani/AfriHG","repo_kind":"official","path":"Multi-Lang-Rouge/tokenizers.py","file_url":"https://github.com/dadelani/AfriHG/blob/HEAD/Multi-Lang-Rouge/tokenizers.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":"0e5615f8994003cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}