{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/alleviating-the-inequality-of-attention-heads","title":"Alleviating the Inequality of Attention Heads for Neural Machine Translation","arxiv_id":"2009.09672","date":"2020-09-21","proceeding":"COLING 2022 10","authors":["Zewei Sun","Shu-Jian Huang","Xin-yu Dai","Jia-Jun Chen"],"abstract":"Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on specific heads. To tackle this problem, we propose a simple masking method: HeadMask, in two specific ways. Experiments show that translation improvements are achieved on multiple language pairs. Subsequent empirical analyses also support our assumption and confirm the effectiveness of the method.","url_abs":"https://arxiv.org/abs/2009.09672v2","url_pdf":"https://arxiv.org/pdf/2009.09672v2.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":"machine-translation","task_name":"Machine Translation"},{"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":[{"leaderboard":"/sota/machine-translation-on-iwslt2015-vietnamese","task":"Machine Translation","dataset":"IWSLT2015 Vietnamese-English","model":"HeadMask (Random-18)","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"26.85"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-iwslt2015-vietnamese","task":"Machine Translation","dataset":"IWSLT2015 Vietnamese-English","model":"HeadMask (Impt-18)","rank_in_archive_order":2,"of":2,"metrics":{"BLEU":"26.36"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","task":"Machine Translation","dataset":"WMT2016 Romanian-English","model":"HeadMask (Impt-18)","rank_in_archive_order":10,"of":21,"metrics":{"BLEU score":"32.95"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2016-romanian","task":"Machine Translation","dataset":"WMT2016 Romanian-English","model":"HeadMask (Random-18)","rank_in_archive_order":13,"of":21,"metrics":{"BLEU score":"32.85"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2017-turkish","task":"Machine Translation","dataset":"WMT2017 Turkish-English","model":"HeadMask (Random-18)","rank_in_archive_order":1,"of":2,"metrics":{"BLEU score":"17.56"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-wmt2017-turkish","task":"Machine Translation","dataset":"WMT2017 Turkish-English","model":"HeadMask (Impt-18)","rank_in_archive_order":2,"of":2,"metrics":{"BLEU score":"17.48"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"cb7ef5b0085d6dbf6bd9c6f861d98ea07f34b1edde5c9c1d2bfd93781b583c2c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}