Language-agnostic BERT Sentence Embedding
Open accessAbstract
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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
BERT embeddings capture rich semantic information and are widely recognized as effective for sentence similarity tasks.
“Previous literature showed the BERT embeddings54 capture rich semantic information and are widely recognized as effective for sentence similarity tasks55–57.”
From Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation (2025) · cites this paper as [55]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · see citing works
Jakubův, J., Chvalovský, K., Goertzel, Z., et al. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,648 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Layer NormalizationPreprint
Ba, J., Kiros, J., & Hinton, G. E. (2016) · arXiv.org · doi:10.48550/arxiv.1607.06450 · Cited by 13,745 · see citing works
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, N., & Gurevych, I. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1410 · Cited by 12,778 · see citing works
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522 · see citing works
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929 · see citing works
Mining and summarizing customer reviews
Hu, M., & Liu, B. (2004) · Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1014052.1014073 · Cited by 7,793 · see citing works
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878 · see citing works
Unsupervised Cross-lingual Representation Learning at Scale
Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.747 · Cited by 5,637 · see citing works
Annotating Expressions of Opinions and Emotions in Language
Wiebe, J., Wilson, T., & Cardie, C. (2005) · Computers and the Humanities · doi:10.1007/s10579-005-7880-9 · Cited by 1,763 · see citing works
Cross-lingual Language Model Pretraining
Lample, G., & Conneau, A. (2019) · arXiv · doi:10.48550/arxiv.1901.07291 · Cited by 1,586 · see citing works
Universal Sentence Encoder for English
Cer, D. M., Yang, Y., Kong, S.-Y., Hua, N., Limtiaco, N., John, R. S., Constant, N., Guajardo-Céspedes, M., Yuan, S., Tar, C., et al. (2018) · Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) · doi:10.18653/v1/d18-2029 · Cited by 1,344 · see citing works
Self-citationCer, D., Yang, Y., Kong, S.-Y., Hua, N., Limtiaco, N., John, R. S., Constant, N., Guajardo-Cespedes, M., Yuan, S., Tar, C., et al. (2018) · arXiv · doi:10.48550/arxiv.1803.11175 · Cited by 1,267 · see citing works
Self-citationUnderstanding Back-Translation at Scale
Edunov, S., Ott, M., Auli, M., & Grangier, D. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1045 · Cited by 1,044 · see citing works
Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation
Reimers, N., & Gurevych, I. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.365 · Cited by 971 · see citing works
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond
Artetxe, M., & Schwenk, H. (2019) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00288 · Cited by 899 · see citing works
A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum CutsPreprint
Pang, B., & Lee, L. (2004) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0409058 · Cited by 789 · see citing works
Pang, B., & Lee, L. (2005) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0506075 · Cited by 744 · see citing works
Multilingual Universal Sentence Encoder for Semantic RetrievalPreprint
Yang, Y., Cer, D. M., Ahmad, A., Guo, M., Law, J., Constant, N., Ábrego, G. H., Yuan, S., Tar, C., Sung, Y.-H., et al. (2019) · Annual Meeting of the Association for Computational Linguistics · doi:10.48550/arxiv.1907.04307 · Cited by 572 · see citing works
Self-citationSentEval: An Evaluation Toolkit for Universal Sentence Representations
Conneau, A., & Kiela, D. (2018) · arXiv · doi:10.48550/arxiv.1803.05449 · Cited by 477 · see citing works
SentEval: An Evaluation Toolkit for Universal Sentence Representations
Conneau, A., & Kiela, D. (2018) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/2gscircifffd · Cited by 477 · see citing works
Building a question answering test collection
Voorhees, E. M., & Tice, D. M. (2000) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/345508.345577 · Cited by 437 · see citing works
An efficient framework for learning sentence representations
Logeswaran, L., & Lee, H. (2018) · arXiv · doi:10.48550/arxiv.1803.02893 · Cited by 427 · see citing works
Multilingual Universal Sentence Encoder for Semantic Retrieval
Yang, Y., Cer, D. M., Ahmad, A., Guo, M., Law, J., Constant, N., Ábrego, G. H., Yuan, S., Tar, C., Sung, Y.-H., et al. (2020) · Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL Demo) · doi:10.18653/v1/2020.acl-demos.12 · Cited by 411 · see citing works
Self-citationXTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual GeneralizationPreprint
Hu, J., Ruder, S., Siddhant, A., Neubig, G., Fırat, O., & Johnson, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.11080 · Cited by 335 · see citing works
When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation?
Ye, Q., Sachan, D. S., Felix, M., Padmanabhan, S. J., & Neubig, G. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-2084 · Cited by 302 · see citing works
Cross-Lingual Ability of Multilingual BERT: An Empirical StudyPreprint
Karthikeyan, K., Wang, Z., Mayhew, S., & Roth, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.07840 · Cited by 301 · see citing works
The United Nations Parallel Corpus v1.0
Ziemski, M., Junczys-Dowmunt, M., & Pouliquen, B. (2016) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/263tmvnpzevv · Cited by 291 · see citing works
Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
Arivazhagan, N., Bapna, A., Firat, O., Lepikhin, D., Johnson, M., Krikun, M., Chen, M. X., Cao, Y., Foster, G., Cherry, C., et al. (2019) · arXiv · doi:10.48550/arxiv.1907.05019 · Cited by 279 · see citing works
Self-citationMargin-based Parallel Corpus Mining with Multilingual Sentence EmbeddingsPreprint
Artetxe, M., & Schwenk, H. (2018) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1309 · Cited by 235 · see citing works
Learning Semantic Textual Similarity from Conversations
Yang, Y., Yuan, S., Cer, D. M., Kong, S.-Y., Constant, N., Pilar, P., Ge, H., Sung, Y.-H., Strope, B. P., & Kurzweil, R. (2018) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w18-3022 · Cited by 148 · see citing works
Self-citationLarge Scale Parallel Document Mining for Machine Translation
Uszkoreit, J., Ponte, J. M., Popat, A. C., & Dubiner, M. (2010) · Cited by 144 · see citing works
The University of Edinburgh's Neural MT Systems for WMT17
Sennrich, R., Birch, A., Currey, A., Germann, U., Haddow, B., Heafield, K., Barone, A. V. M., & Williams, P. J. (2017) · Conference on Machine Translation (WMT) · doi:10.18653/v1/w17-4739 · Cited by 134 · see citing works
Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model
Chidambaram, M., Yang, Y., Cer, D. M., Yuan, S., Sung, Y.-H., Strope, B. P., & Kurzweil, R. (2019) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w19-4330 · Cited by 124 · see citing works
Self-citationYang, Y., Ábrego, G. H., Yuan, S., Guo, M., Shen, Q., Cer, D. M., Sung, Y.-H., Strope, B. P., & Kurzweil, R. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/746 · Cited by 110 · see citing works
Self-citationEffective Parallel Corpus Mining using Bilingual Sentence Embeddings
Guo, M., Shen, Q., Yang, Y., Ge, H., Cer, D. M., Ábrego, G. H., Stevens, K., Constant, N., Sung, Y.-H., Strope, B. P., et al. (2018) · Conference on Machine Translation (WMT) · doi:10.18653/v1/w18-6317 · Cited by 105 · see citing works
Self-citationDenoising Neural Machine Translation Training with Trusted Data and Online Data Selection
Wang, W., Watanabe, T., Hughes, M., Nakagawa, T., & Chelba, C. (2018) · Conference on Machine Translation · doi:10.18653/v1/w18-6314 · Cited by 94 · see citing works
Self-citationEfficient Training of BERT by Progressively Stacking
Gong, L., He, D., Li, Z., et al. (2019) · International Conference on Machine Learning · Cited by 66 · see citing works
Massively Multilingual Neural Machine TranslationPreprint
Aharoni, R., Johnson, M., & Fırat, O. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.00089 · Cited by 41 · see citing works
Overview of the Third BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora
Zweigenbaum, P., Sharoff, S., & Rapp, R. (2018) · HAL (Le Centre pour la Communication Scientifique Directe) · Cited by 35 · see citing works
Nearest Neighbor Search in Google Correlate
Vanderkam, D., Schonberger, R., Rowley, H. A., et al. (2013) · Cited by 28 · see citing works
The University of Edinburgh's Neural MT Systems for WMT17Preprint
Sennrich, R., Birch, A., Currey, A., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.00726 · Cited by 22 · see citing works
Neural Passage Retrieval with Improved Negative ContrastPreprint
Lu, J. R., Ábrego, G. H., Ma, J., Ni, J., & Yang, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12523 · Cited by 21 · see citing works
Self-citationUniversal Sentence Representation Learning with Conditional Masked Language ModelPreprint
Yang, Z., Yang, Y., Cer, D. M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.14388 · Cited by 16 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 7
- Daniel Cer, Mona Diab, Eneko Agirre, Iñigo Lopez- Gazpio, and Lucia Specia. 2017. SemEval-2017 task 1: Semantic textual similarity multilingual and crosslingual focused evaluation. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 1-14, Vancouver, Canada. Association for Computational Linguistics. · DOI · Paper page
- Muthuraman Chidambaram, Yinfei Yang, Daniel Cer, Steve Yuan, Yun-Hsuan Sung, Brian Strope, and Ray Kurzweil. 2018. Learning cross-lingual sentence representations via a multi-task dual-encoder model. CoRR, abs/1810.12836. · arXiv
- Alexis Conneau, Douwe Kiela, Holger Schwenk, Loïc Barrault, and Antoine Bordes. 2017. Supervised learning of universal sentence representations from natural language inference data. In Proceedings of the 2017 Conference on Empirical Methods in Nat- ural Language Processing, pages 670-680, Copen- hagen, Denmark. Association for Computational Linguistics.
- William Dolan, Chris Quirk, Chris Brockett, and Bill Dolan. 2004. Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources. International Conference on Compu- tational Linguistics.
- Lajanugen Logeswaran and Honglak Lee. 2018. An ef- ficient framework for learning sentence representa- tions. In International Conference on Learning Rep- resentations (ICLR).
- Holger Schwenk, Guillaume Wenzek, Sergey Edunov, E. Grave, and Armand Joulin. 2019. Ccmatrix: Min- ing billions of high-quality parallel sentences on the web. ArXiv, abs/1911.04944. · arXiv
- Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural machine translation of rare words with subword units. In Proceedings of the 54th An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1715- 1725, Berlin, Germany. Association for Computa- tional Linguistics. · DOI · Paper page
Cited by
Sorted by citations
How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., Kim, Y. J., Afify, M., & Awadalla, H. H. (2023) · arXiv · doi:10.48550/arxiv.2302.09210 · Cited by 202 · see citing works
“• Quality: To ensure high quality shots we sort our training data using LaBSE (Feng et al., 2020).”
MethodInfluentialTowards a holistic framework for multimodal LLM in 3D brain CT radiology report generation
Li, C.-Y., Chang, K.-J., Yang, C.-F., Wu, H.-Y., Chen, W., Bansal, H., Chen, L., Yang, Y.-P., Chen, Y.-C., Chen, S.-P., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-57426-0 · Cited by 75 · see citing works
“This list is not merely a compilation of keywords but also includes synonyms, enabling the system to recognize a broader array of related terms that may appear in different contexts.”
Self-citationHuman-centered neural reasoning for subjective content processing: Hate speech, emotions, and humor
Kazienko, P., Bielaniewicz, J., Gruza, M., Kanclerz, K., Karanowski, K., Miłkowski, P., & Kocoń, J. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.01.010 · Cited by 38 · see citing works
Kazi, S., Khoja, S., & Daud, A. (2025) · Computer Science Review · doi:10.1016/j.cosrev.2025.100756 · Cited by 9 · see citing works
Enabling Efficient Batch Serving for LMaaS via Generation Length Prediction
Cheng, K., Hu, W., Wang, Z., Du, P., Li, J., & Zhang, S. (2024) · arXiv · doi:10.48550/arxiv.2406.04785 · Cited by 7 · see citing works
- Authors
- Feng, F., Yang, Y., Cer, D., Arivazhagan, N., & Wang, W.
- Affiliations
- Google (United States) (US)
- ORCID
- Arivazhagan, Naveen
- Venue
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2022
- Pages
- 878-891
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W3039695075
- Cited by
- 758
- References
- 45
- Citations by year
- 2026: 105 · 2025: 151 · 2024: 118 · 2023: 172 · 2022: 114 · 2021: 89 · 2020: 8 · 2019: 1
- FWCI
- 76.67
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- multilingual sentence embeddings, BERT, masked language modeling, transfer learning, parallel data, multilingual language models, Chinese-English machine translation, Tatoeba, Common Crawl
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
