{"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/multi-task-learning-for-zero-shot-performance","title":"Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models","arxiv_id":"2205.06130","date":"2022-05-12","proceeding":"ACL 2022 5","authors":["Kabir Ahuja","Shanu Kumar","Sandipan Dandapat","Monojit Choudhury"],"abstract":"Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from language to language depending on the pivot language(s) used for fine-tuning. In this work, we build upon some of the existing techniques for predicting the zero-shot performance on a task, by modeling it as a multi-task learning problem. We jointly train predictive models for different tasks which helps us build more accurate predictors for tasks where we have test data in very few languages to measure the actual performance of the model. Our approach also lends us the ability to perform a much more robust feature selection and identify a common set of features that influence zero-shot performance across a variety of tasks.","url_abs":"https://arxiv.org/abs/2205.06130v1","url_pdf":"https://arxiv.org/pdf/2205.06130v1.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":[],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feature-selection","method_name":"Feature Selection"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.06130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.06130"}},"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/hichamjanati/mutar","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":8},"by_repo_kind":{"found_in_text":{"samples":8,"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":"2225290e7d8cc429","entry":"barycenterkl","repo":"hichamjanati/mutar","repo_kind":"found_in_text","path":"mutar/otfunctions.py","file_url":"https://github.com/hichamjanati/mutar/blob/HEAD/mutar/otfunctions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2225290e7d8cc429"}},{"code_sha256_prefix":"441152b0bb6e215a","entry":"barycenterkl_log","repo":"hichamjanati/mutar","repo_kind":"found_in_text","path":"mutar/otfunctions.py","file_url":"https://github.com/hichamjanati/mutar/blob/HEAD/mutar/otfunctions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"441152b0bb6e215a"}},{"code_sha256_prefix":"9ef314913156dc20","entry":"groundmetric","repo":"hichamjanati/mutar","repo_kind":"found_in_text","path":"mutar/utils.py","file_url":"https://github.com/hichamjanati/mutar/blob/HEAD/mutar/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9ef314913156dc20"}},{"code_sha256_prefix":"8765de0d7fb7f39f","entry":"groundmetric_img","repo":"hichamjanati/mutar","repo_kind":"found_in_text","path":"mutar/utils.py","file_url":"https://github.com/hichamjanati/mutar/blob/HEAD/mutar/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8765de0d7fb7f39f"}},{"code_sha256_prefix":"b4a8a1feba8a0ec5","entry":"residual","repo":"hichamjanati/mutar","repo_kind":"found_in_text","path":"mutar/utils.py","file_url":"https://github.com/hichamjanati/mutar/blob/HEAD/mutar/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b4a8a1feba8a0ec5"}},{"code_sha256_prefix":"1931d3414a66c16b","entry":"solver_lasso","repo":"hichamjanati/mutar","repo_kind":"found_in_text","path":"mutar/solvers.py","file_url":"https://github.com/hichamjanati/mutar/blob/HEAD/mutar/solvers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1931d3414a66c16b"}},{"code_sha256_prefix":"2cdbb52c4b3faccc","entry":"solver_mll","repo":"hichamjanati/mutar","repo_kind":"found_in_text","path":"mutar/solvers.py","file_url":"https://github.com/hichamjanati/mutar/blob/HEAD/mutar/solvers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2cdbb52c4b3faccc"}},{"code_sha256_prefix":"70e5e8fff27f3426","entry":"wklobjective_converged","repo":"hichamjanati/mutar","repo_kind":"found_in_text","path":"mutar/otfunctions.py","file_url":"https://github.com/hichamjanati/mutar/blob/HEAD/mutar/otfunctions.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"70e5e8fff27f3426"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}