{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/language-agnostic-bert-sentence-embedding","title":"Language-agnostic BERT Sentence Embedding","arxiv_id":"2007.01852","date":"2020-07-03","proceeding":"ACL 2022 5","authors":["Fangxiaoyu Feng","Yinfei Yang","Daniel Cer","Naveen Arivazhagan","Wei Wang"],"abstract":"While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT based cross-lingual sentence embeddings have yet to be explored. We systematically investigate methods for learning multilingual sentence embeddings by combining the best methods for learning monolingual and cross-lingual representations including: masked language modeling (MLM), translation language modeling (TLM) (Conneau and Lample, 2019), dual encoder translation ranking (Guo et al., 2018), and additive margin softmax (Yang et al., 2019a). We show that introducing a pre-trained multilingual language model dramatically reduces the amount of parallel training data required to achieve good performance by 80%. Composing the best of these methods produces a model that achieves 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba, well above the 65.5% achieved by Artetxe and Schwenk (2019b), while still performing competitively on monolingual transfer learning benchmarks (Conneau and Kiela, 2018). Parallel data mined from CommonCrawl using our best model is shown to train competitive NMT models for en-zh and en-de. We publicly release our best multilingual sentence embedding model for 109+ languages at https://tfhub.dev/google/LaBSE.","url_abs":"https://arxiv.org/abs/2007.01852v2","url_pdf":"https://arxiv.org/pdf/2007.01852v2.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":"language-agnostic-bert-sentence-embedding","repo_url":"https://github.com/FreddeFrallan/Multilingual-CLIP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-agnostic-bert-sentence-embedding","repo_url":"https://github.com/bojone/labse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"language-agnostic-bert-sentence-embedding","repo_url":"https://github.com/jeongukjae/smaller-labse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"language-agnostic-bert-sentence-embedding","repo_url":"https://github.com/s-nlp/russe_detox_2022","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"language-agnostic-bert-sentence-embedding","repo_url":"https://github.com/setu4993/convert-labse-tf-pt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"language-agnostic-bert-sentence-embedding","repo_url":"https://github.com/skoltech-nlp/russe_detox_2022","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"masked-language-modeling","task_name":"Masked Language Modeling"},{"task_slug":"multilingual-nlp","task_name":"Multilingual NLP"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"},{"task_slug":"sentence-embedding-1","task_name":"Sentence-Embedding"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"}],"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":"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":{"syntology_url":"https://syntology.ai/paper/2007.01852","atlas_url":"https://app.syntology.ai/?focus=2007.01852","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2007.01852"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2007.01852\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2007.01852"},"call":"get_concepts_for_paper(arxiv_id=\"2007.01852\")"}],"by_repo":[{"repo":"FreddeFrallan/Multilingual-CLIP","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2109.07622"],"harvested_for_calls":[{"arxiv_id":"2109.07622","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2109.07622"},"call":"get_harvested_code_for_paper(arxiv_id=\"2109.07622\")"}]},{"repo":"bojone/labse","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jeongukjae/smaller-labse","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"s-nlp/russe_detox_2022","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"setu4993/convert-labse-tf-pt","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"skoltech-nlp/russe_detox_2022","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1d848b27c13a8be739a5faec5aa8cffb8739f418200dfc7bc66c23cbb671ae13","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}