{"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/wider-closer-mixture-of-short-channel","title":"WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition","arxiv_id":"2212.03506","date":"2022-12-07","proceeding":null,"authors":["Jun-Yu Ma","Beiduo Chen","Jia-Chen Gu","Zhen-Hua Ling","Wu Guo","Quan Liu","Zhigang Chen","Cong Liu"],"abstract":"Zero-shot cross-lingual named entity recognition (NER) aims at transferring knowledge from annotated and rich-resource data in source languages to unlabeled and lean-resource data in target languages. Existing mainstream methods based on the teacher-student distillation framework ignore the rich and complementary information lying in the intermediate layers of pre-trained language models, and domain-invariant information is easily lost during transfer. In this study, a mixture of short-channel distillers (MSD) method is proposed to fully interact the rich hierarchical information in the teacher model and to transfer knowledge to the student model sufficiently and efficiently. Concretely, a multi-channel distillation framework is designed for sufficient information transfer by aggregating multiple distillers as a mixture. Besides, an unsupervised method adopting parallel domain adaptation is proposed to shorten the channels between the teacher and student models to preserve domain-invariant features. Experiments on four datasets across nine languages demonstrate that the proposed method achieves new state-of-the-art performance on zero-shot cross-lingual NER and shows great generalization and compatibility across languages and fields.","url_abs":"https://arxiv.org/abs/2212.03506v1","url_pdf":"https://arxiv.org/pdf/2212.03506v1.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":"wider-closer-mixture-of-short-channel","repo_url":"https://github.com/mckysse/msd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"cross-lingual-ner","task_name":"Cross-Lingual NER"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.03506","atlas_url":"https://app.syntology.ai/?focus=2212.03506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03506"}},"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/mckysse/msd","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":3,"ran":5,"ran_honours":4,"unverified":2},"by_repo_kind":{"official":{"samples":14,"ran":12,"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":"0f786c407fb1ee4c","entry":"swish","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_openai.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_openai.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"671a619bed5669a3","entry":"angle_defn","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_ctrl.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_ctrl.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"671a619bed5669a3"}},{"code_sha256_prefix":"8d23fbe2b99b840b","entry":"gelu","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_gpt2.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_gpt2.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8d23fbe2b99b840b"}},{"code_sha256_prefix":"211753ba29188d4e","entry":"gelu","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_bert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"211753ba29188d4e"}},{"code_sha256_prefix":"9bc31d06256e1691","entry":"gelu","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_tf_bert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_tf_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9bc31d06256e1691"}},{"code_sha256_prefix":"69c6d14de8190cfb","entry":"gelu","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_distilbert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_distilbert.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"69c6d14de8190cfb"}},{"code_sha256_prefix":"77601724cad03f95","entry":"gelu_new","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_bert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"77601724cad03f95"}},{"code_sha256_prefix":"83257a2b015273fa","entry":"gelu_new","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_tf_bert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_tf_bert.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"83257a2b015273fa"}},{"code_sha256_prefix":"0c145728a35789fa","entry":"load_tf_weights_in_bert","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_bert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0c145728a35789fa"}},{"code_sha256_prefix":"59ac77747a12b1cb","entry":"positional_encoding","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_ctrl.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_ctrl.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"59ac77747a12b1cb"}},{"code_sha256_prefix":"57ebc1447d921c46","entry":"scaled_dot_product_attention","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_ctrl.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_ctrl.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"57ebc1447d921c46"}},{"code_sha256_prefix":"86d13b9f67274f19","entry":"swish","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_tf_bert.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_tf_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86d13b9f67274f19"}},{"code_sha256_prefix":"654e91efc679fe84","entry":"load_tf_weights_in_gpt2","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_gpt2.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_gpt2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"654e91efc679fe84"}},{"code_sha256_prefix":"42ee168c3ae12e60","entry":"load_tf_weights_in_openai_gpt","repo":"mckysse/msd","repo_kind":"official","path":"transformers/modeling_openai.py","file_url":"https://github.com/mckysse/msd/blob/HEAD/transformers/modeling_openai.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42ee168c3ae12e60"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}