{"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/everything-is-all-it-takes-a-multipronged","title":"Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction","arxiv_id":"2109.06798","date":"2021-09-14","proceeding":"EMNLP 2021 11","authors":["Mahsa Yarmohammadi","Shijie Wu","Marc Marone","Haoran Xu","Seth Ebner","Guanghui Qin","Yunmo Chen","Jialiang Guo","Craig Harman","Kenton Murray","Aaron Steven White","Mark Dredze","Benjamin Van Durme"],"abstract":"Zero-shot cross-lingual information extraction (IE) describes the construction of an IE model for some target language, given existing annotations exclusively in some other language, typically English. While the advance of pretrained multilingual encoders suggests an easy optimism of \"train on English, run on any language\", we find through a thorough exploration and extension of techniques that a combination of approaches, both new and old, leads to better performance than any one cross-lingual strategy in particular. We explore techniques including data projection and self-training, and how different pretrained encoders impact them. We use English-to-Arabic IE as our initial example, demonstrating strong performance in this setting for event extraction, named entity recognition, part-of-speech tagging, and dependency parsing. We then apply data projection and self-training to three tasks across eight target languages. Because no single set of techniques performs the best across all tasks, we encourage practitioners to explore various configurations of the techniques described in this work when seeking to improve on zero-shot training.","url_abs":"https://arxiv.org/abs/2109.06798v1","url_pdf":"https://arxiv.org/pdf/2109.06798v1.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":"everything-is-all-it-takes-a-multipronged","repo_url":"https://github.com/shijie-wu/crosslingual-nlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"everything-is-all-it-takes-a-multipronged","repo_url":"https://github.com/kentonmurray/arabicdetokenizer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"event-extraction","task_name":"Event Extraction"},{"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":"part-of-speech-tagging","task_name":"Part-Of-Speech Tagging"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.06798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.06798"}},"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/shijie-wu/crosslingual-nlp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kentonmurray/arabicdetokenizer","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"ran":1,"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":"7c508037b40522af","entry":"str2bool","repo":"shijie-wu/crosslingual-nlp","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/shijie-wu/crosslingual-nlp/blob/HEAD/src/util.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c508037b40522af"}},{"code_sha256_prefix":"488dba8d177c9928","entry":"convert_bio_to_spans","repo":"shijie-wu/crosslingual-nlp","repo_kind":"official","path":"src/metric.py","file_url":"https://github.com/shijie-wu/crosslingual-nlp/blob/HEAD/src/metric.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":"488dba8d177c9928"}},{"code_sha256_prefix":"b98af3f89f51db91","entry":"get_inverse_square_root_schedule_with_warmup","repo":"shijie-wu/crosslingual-nlp","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/shijie-wu/crosslingual-nlp/blob/HEAD/src/util.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":"b98af3f89f51db91"}},{"code_sha256_prefix":"03cef9d6feb24fdf","entry":"get_linear_schedule_with_warmup","repo":"shijie-wu/crosslingual-nlp","repo_kind":"official","path":"src/util.py","file_url":"https://github.com/shijie-wu/crosslingual-nlp/blob/HEAD/src/util.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":"03cef9d6feb24fdf"}},{"code_sha256_prefix":"e5ba3e23a1023917","entry":"get_model_path","repo":"shijie-wu/crosslingual-nlp","repo_kind":"official","path":"src/predict.py","file_url":"https://github.com/shijie-wu/crosslingual-nlp/blob/HEAD/src/predict.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":"e5ba3e23a1023917"}},{"code_sha256_prefix":"39b50c340d53bc68","entry":"recover_escape","repo":"shijie-wu/crosslingual-nlp","repo_kind":"official","path":"src/dataset/ace_util.py","file_url":"https://github.com/shijie-wu/crosslingual-nlp/blob/HEAD/src/dataset/ace_util.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":"39b50c340d53bc68"}},{"code_sha256_prefix":"20ba5a5710e57c20","entry":"to_tensor","repo":"shijie-wu/crosslingual-nlp","repo_kind":"official","path":"src/metric.py","file_url":"https://github.com/shijie-wu/crosslingual-nlp/blob/HEAD/src/metric.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":"20ba5a5710e57c20"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}