{"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-contextualized-topic-models","title":"Cross-lingual Contextualized Topic Models with Zero-shot Learning","arxiv_id":"2004.07737","date":"2020-04-16","proceeding":"EACL 2021 2","authors":["Federico Bianchi","Silvia Terragni","Dirk Hovy","Debora Nozza","Elisabetta Fersini"],"abstract":"Many data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to be either single-language or suffer from a huge, but extremely sparse vocabulary. Both issues can be addressed by transfer learning. In this paper, we introduce a zero-shot cross-lingual topic model. Our model learns topics on one language (here, English), and predicts them for unseen documents in different languages (here, Italian, French, German, and Portuguese). We evaluate the quality of the topic predictions for the same document in different languages. Our results show that the transferred topics are coherent and stable across languages, which suggests exciting future research directions.","url_abs":"https://arxiv.org/abs/2004.07737v2","url_pdf":"https://arxiv.org/pdf/2004.07737v2.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-contextualized-topic-models","repo_url":"https://github.com/MilaNLProc/contextualized-topic-models","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"cross-lingual-contextualized-topic-models","repo_url":"https://github.com/aaronmueller/contextualized-topic-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"topic-models","task_name":"Topic Models"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"contextualized-topic-models","method_name":"Contextualized Topic Models"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.07737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.07737"}},"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/MilaNLProc/contextualized-topic-models","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aaronmueller/contextualized-topic-models","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":5,"ran":0,"repositories":1},"listed":{"samples":2,"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":"b0c176c7853fcf40","entry":"get_bag_of_words","repo":"MilaNLProc/contextualized-topic-models","repo_kind":"official","path":"contextualized_topic_models/utils/data_preparation.py","file_url":"https://github.com/MilaNLProc/contextualized-topic-models/blob/HEAD/contextualized_topic_models/utils/data_preparation.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":"b0c176c7853fcf40"}},{"code_sha256_prefix":"2bab4ca3b1881667","entry":"get_bag_of_words","repo":"aaronmueller/contextualized-topic-models","repo_kind":"listed","path":"contextualized_topic_models/utils/data_preparation.py","file_url":"https://github.com/aaronmueller/contextualized-topic-models/blob/HEAD/contextualized_topic_models/utils/data_preparation.py","link_basis":"harvester_set","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":"2bab4ca3b1881667"}},{"code_sha256_prefix":"7e573106cb435fab","entry":"kl_div","repo":"MilaNLProc/contextualized-topic-models","repo_kind":"official","path":"contextualized_topic_models/evaluation/measures.py","file_url":"https://github.com/MilaNLProc/contextualized-topic-models/blob/HEAD/contextualized_topic_models/evaluation/measures.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":"7e573106cb435fab"}},{"code_sha256_prefix":"dcddf652ee7fa2f2","entry":"load_topics","repo":"aaronmueller/contextualized-topic-models","repo_kind":"listed","path":"sample_docs_per_topic.py","file_url":"https://github.com/aaronmueller/contextualized-topic-models/blob/HEAD/sample_docs_per_topic.py","link_basis":"harvester_set","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":"dcddf652ee7fa2f2"}},{"code_sha256_prefix":"f023d128a418f9ec","entry":"overlap","repo":"MilaNLProc/contextualized-topic-models","repo_kind":"official","path":"contextualized_topic_models/evaluation/rbo/rbo.py","file_url":"https://github.com/MilaNLProc/contextualized-topic-models/blob/HEAD/contextualized_topic_models/evaluation/rbo/rbo.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":"f023d128a418f9ec"}},{"code_sha256_prefix":"d210d869cd7f10c9","entry":"raw_overlap","repo":"MilaNLProc/contextualized-topic-models","repo_kind":"official","path":"contextualized_topic_models/evaluation/rbo/rbo.py","file_url":"https://github.com/MilaNLProc/contextualized-topic-models/blob/HEAD/contextualized_topic_models/evaluation/rbo/rbo.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":"d210d869cd7f10c9"}},{"code_sha256_prefix":"e6436bd35135088d","entry":"set_at_depth","repo":"MilaNLProc/contextualized-topic-models","repo_kind":"official","path":"contextualized_topic_models/evaluation/rbo/rbo.py","file_url":"https://github.com/MilaNLProc/contextualized-topic-models/blob/HEAD/contextualized_topic_models/evaluation/rbo/rbo.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":"e6436bd35135088d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}