{"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/cross-lingual-alignment-of-contextual-word","title":"Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing","arxiv_id":"1902.09492","date":"2019-02-25","proceeding":"NAACL 2019 6","authors":["Tal Schuster","Ori Ram","Regina Barzilay","Amir Globerson"],"abstract":"We introduce a novel method for multilingual transfer that utilizes deep\ncontextual embeddings, pretrained in an unsupervised fashion. While contextual\nembeddings have been shown to yield richer representations of meaning compared\nto their static counterparts, aligning them poses a challenge due to their\ndynamic nature. To this end, we construct context-independent variants of the\noriginal monolingual spaces and utilize their mapping to derive an alignment\nfor the context-dependent spaces. This mapping readily supports processing of a\ntarget language, improving transfer by context-aware embeddings. Our\nexperimental results demonstrate the effectiveness of this approach for\nzero-shot and few-shot learning of dependency parsing. Specifically, our method\nconsistently outperforms the previous state-of-the-art on 6 tested languages,\nyielding an improvement of 6.8 LAS points on average.","url_abs":"http://arxiv.org/abs/1902.09492v2","url_pdf":"http://arxiv.org/pdf/1902.09492v2.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":"cross-lingual-alignment-of-contextual-word","repo_url":"https://github.com/TalSchuster/CrossLingualELMo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"cross-lingual-alignment-of-contextual-word","repo_url":"https://github.com/TalSchuster/CrossLingualContextualEmb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-zero-shot-dependency-parsing","task_name":"Cross-lingual zero-shot dependency parsing"},{"task_slug":"dependency-parsing","task_name":"Dependency Parsing"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-lingual-zero-shot-dependency-parsing-on","task":"Cross-lingual zero-shot dependency parsing","dataset":"Universal Dependency Treebank","model":"Cross-Lingual ELMo","rank_in_archive_order":1,"of":3,"metrics":{"LAS":"77.3","UAS":"84.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.09492","atlas_url":"https://app.syntology.ai/?focus=1902.09492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09492"}},"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/TalSchuster/CrossLingualContextualEmb","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TalSchuster/CrossLingualELMo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1},"listed":{"samples":1,"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":"bb82d774315a83d6","entry":"parse_config","repo":"TalSchuster/CrossLingualContextualEmb","repo_kind":"listed","path":"gen_anchors.py","file_url":"https://github.com/TalSchuster/CrossLingualContextualEmb/blob/HEAD/gen_anchors.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb82d774315a83d6"}},{"code_sha256_prefix":"6d45258b5c56fb25","entry":"read_examples","repo":"TalSchuster/CrossLingualELMo","repo_kind":"official","path":"gen_anchors_bert.py","file_url":"https://github.com/TalSchuster/CrossLingualELMo/blob/HEAD/gen_anchors_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d45258b5c56fb25"}},{"code_sha256_prefix":"782d3e4b79c2b168","entry":"convert_examples_to_features","repo":"TalSchuster/CrossLingualELMo","repo_kind":"official","path":"gen_anchors_bert.py","file_url":"https://github.com/TalSchuster/CrossLingualELMo/blob/HEAD/gen_anchors_bert.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":"782d3e4b79c2b168"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}