{"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/improving-pretrained-cross-lingual-language","title":"Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment","arxiv_id":"2106.06381","date":"2021-06-11","proceeding":"ACL 2021 5","authors":["Zewen Chi","Li Dong","Bo Zheng","Shaohan Huang","Xian-Ling Mao","Heyan Huang","Furu Wei"],"abstract":"The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences. In this paper, we introduce denoising word alignment as a new cross-lingual pre-training task. Specifically, the model first self-labels word alignments for parallel sentences. Then we randomly mask tokens in a bitext pair. Given a masked token, the model uses a pointer network to predict the aligned token in the other language. We alternately perform the above two steps in an expectation-maximization manner. Experimental results show that our method improves cross-lingual transferability on various datasets, especially on the token-level tasks, such as question answering, and structured prediction. Moreover, the model can serve as a pretrained word aligner, which achieves reasonably low error rates on the alignment benchmarks. The code and pretrained parameters are available at https://github.com/CZWin32768/XLM-Align.","url_abs":"https://arxiv.org/abs/2106.06381v2","url_pdf":"https://arxiv.org/pdf/2106.06381v2.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":"improving-pretrained-cross-lingual-language","repo_url":"https://github.com/CZWin32768/XLM-Align","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"structured-prediction","task_name":"Structured Prediction"},{"task_slug":"word-alignment","task_name":"Word Alignment"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"pointer-net","method_name":"Pointer Network"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.06381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06381"}},"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/CZWin32768/XLM-Align","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"010980bf6b0dffd6","entry":"_sinkhorn_iter","repo":"CZWin32768/XLM-Align","repo_kind":"official","path":"word_aligner/xlmalign-ot-aligner.py","file_url":"https://github.com/CZWin32768/XLM-Align/blob/HEAD/word_aligner/xlmalign-ot-aligner.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"010980bf6b0dffd6"}},{"code_sha256_prefix":"269578f65f3f34dc","entry":"extract_wa_from_pi_xi","repo":"CZWin32768/XLM-Align","repo_kind":"official","path":"word_aligner/xlmalign-ot-aligner.py","file_url":"https://github.com/CZWin32768/XLM-Align/blob/HEAD/word_aligner/xlmalign-ot-aligner.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"269578f65f3f34dc"}},{"code_sha256_prefix":"c5bc5e64bf6f281c","entry":"sinkhorn","repo":"CZWin32768/XLM-Align","repo_kind":"official","path":"word_aligner/xlmalign-ot-aligner.py","file_url":"https://github.com/CZWin32768/XLM-Align/blob/HEAD/word_aligner/xlmalign-ot-aligner.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5bc5e64bf6f281c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}