{"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/enhancing-cross-lingual-natural-language-1","title":"Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer","arxiv_id":"2305.12761","date":"2023-05-22","proceeding":null,"authors":["Shuang Li","Xuming Hu","Aiwei Liu","Yawen Yang","Fukun Ma","Philip S. Yu","Lijie Wen"],"abstract":"Cross-lingual natural language inference is a fundamental problem in cross-lingual language understanding. Many recent works have used prompt learning to address the lack of annotated parallel corpora in XNLI. However, these methods adopt discrete prompting by simply translating the templates to the target language and need external expert knowledge to design the templates. Besides, discrete prompts of human-designed template words are not trainable vectors and can not be migrated to target languages in the inference stage flexibly. In this paper, we propose a novel Soft prompt learning framework with the Multilingual Verbalizer (SoftMV) for XNLI. SoftMV first constructs cloze-style question with soft prompts for the input sample. Then we leverage bilingual dictionaries to generate an augmented multilingual question for the original question. SoftMV adopts a multilingual verbalizer to align the representations of original and augmented multilingual questions into the same semantic space with consistency regularization. Experimental results on XNLI demonstrate that SoftMV can achieve state-of-the-art performance and significantly outperform the previous methods under the few-shot and full-shot cross-lingual transfer settings.","url_abs":"https://arxiv.org/abs/2305.12761v1","url_pdf":"https://arxiv.org/pdf/2305.12761v1.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":"enhancing-cross-lingual-natural-language-1","repo_url":"https://github.com/thu-bpm/softmv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-lingual-natural-language-inference","task_name":"Cross-Lingual Natural Language Inference"},{"task_slug":"cross-lingual-transfer","task_name":"Cross-Lingual Transfer"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.12761","atlas_url":"https://app.syntology.ai/?focus=2305.12761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.12761"}},"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/thu-bpm/softmv","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"a8b5f463c95e7ba4","entry":"eq_div","repo":"thu-bpm/softmv","repo_kind":"official","path":"prompt/utils.py","file_url":"https://github.com/thu-bpm/softmv/blob/HEAD/prompt/utils.py","link_basis":"first_harvest_node","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":"a8b5f463c95e7ba4"}},{"code_sha256_prefix":"999a29a2aa943ed5","entry":"get_logger","repo":"thu-bpm/softmv","repo_kind":"official","path":"log.py","file_url":"https://github.com/thu-bpm/softmv/blob/HEAD/log.py","link_basis":"first_harvest_node","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":"999a29a2aa943ed5"}},{"code_sha256_prefix":"cdc3095e36a5efa7","entry":"lowercase_first","repo":"thu-bpm/softmv","repo_kind":"official","path":"prompt/utils.py","file_url":"https://github.com/thu-bpm/softmv/blob/HEAD/prompt/utils.py","link_basis":"first_harvest_node","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":"cdc3095e36a5efa7"}},{"code_sha256_prefix":"20e328b05dd717e0","entry":"remove_final_punc","repo":"thu-bpm/softmv","repo_kind":"official","path":"prompt/utils.py","file_url":"https://github.com/thu-bpm/softmv/blob/HEAD/prompt/utils.py","link_basis":"first_harvest_node","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":"20e328b05dd717e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}