{"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/on-the-strengths-of-cross-attention-in","title":"Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation","arxiv_id":"2104.08771","date":"2021-04-18","proceeding":"EMNLP 2021 11","authors":["Mozhdeh Gheini","Xiang Ren","Jonathan May"],"abstract":"We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series of experiments through fine-tuning a translation model on data where either the source or target language has changed. These experiments reveal that fine-tuning only the cross-attention parameters is nearly as effective as fine-tuning all parameters (i.e., the entire translation model). We provide insights into why this is the case and observe that limiting fine-tuning in this manner yields cross-lingually aligned embeddings. The implications of this finding for researchers and practitioners include a mitigation of catastrophic forgetting, the potential for zero-shot translation, and the ability to extend machine translation models to several new language pairs with reduced parameter storage overhead.","url_abs":"https://arxiv.org/abs/2104.08771v2","url_pdf":"https://arxiv.org/pdf/2104.08771v2.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":"on-the-strengths-of-cross-attention-in","repo_url":"https://github.com/mgheini/xattn-transfer-for-mt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"}],"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":"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":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2104.08771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08771"}},"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/mgheini/xattn-transfer-for-mt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"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":"2e69129bbcf930e7","entry":"distributed_init","repo":"mgheini/xattn-transfer-for-mt","repo_kind":"official","path":"fairseq-modified/fairseq/distributed_utils.py","file_url":"https://github.com/mgheini/xattn-transfer-for-mt/blob/HEAD/fairseq-modified/fairseq/distributed_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e69129bbcf930e7"}},{"code_sha256_prefix":"90b79fe15491de83","entry":"is_master","repo":"mgheini/xattn-transfer-for-mt","repo_kind":"official","path":"fairseq-modified/fairseq/distributed_utils.py","file_url":"https://github.com/mgheini/xattn-transfer-for-mt/blob/HEAD/fairseq-modified/fairseq/distributed_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90b79fe15491de83"}},{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"mgheini/xattn-transfer-for-mt","repo_kind":"official","path":"fairseq-modified/fairseq/binarizer.py","file_url":"https://github.com/mgheini/xattn-transfer-for-mt/blob/HEAD/fairseq-modified/fairseq/binarizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82bdf940665aeeb4"}},{"code_sha256_prefix":"9418b43048e4e4ec","entry":"url_to_filename","repo":"mgheini/xattn-transfer-for-mt","repo_kind":"official","path":"fairseq-modified/fairseq/file_utils.py","file_url":"https://github.com/mgheini/xattn-transfer-for-mt/blob/HEAD/fairseq-modified/fairseq/file_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9418b43048e4e4ec"}},{"code_sha256_prefix":"199e96db5edd0edd","entry":"all_reduce","repo":"mgheini/xattn-transfer-for-mt","repo_kind":"official","path":"fairseq-modified/fairseq/distributed_utils.py","file_url":"https://github.com/mgheini/xattn-transfer-for-mt/blob/HEAD/fairseq-modified/fairseq/distributed_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"199e96db5edd0edd"}},{"code_sha256_prefix":"b1a033619f614e17","entry":"filename_to_url","repo":"mgheini/xattn-transfer-for-mt","repo_kind":"official","path":"fairseq-modified/fairseq/file_utils.py","file_url":"https://github.com/mgheini/xattn-transfer-for-mt/blob/HEAD/fairseq-modified/fairseq/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b1a033619f614e17"}},{"code_sha256_prefix":"bd3fe80662b28bc7","entry":"load_archive_file","repo":"mgheini/xattn-transfer-for-mt","repo_kind":"official","path":"fairseq-modified/fairseq/file_utils.py","file_url":"https://github.com/mgheini/xattn-transfer-for-mt/blob/HEAD/fairseq-modified/fairseq/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd3fe80662b28bc7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}