{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T02:59:23Z","timestamp":1775789963730,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61702516"],"award-info":[{"award-number":["61702516"]}]},{"name":"National Natural Science Foundation of China","award":["JJ-2022-719-02"],"award-info":[{"award-number":["JJ-2022-719-02"]}]},{"name":"Innovation Fund of the Maritime Defense Technology Innovation Center","award":["61702516"],"award-info":[{"award-number":["61702516"]}]},{"name":"Innovation Fund of the Maritime Defense Technology Innovation Center","award":["JJ-2022-719-02"],"award-info":[{"award-number":["JJ-2022-719-02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The pursuit of universal, symmetric semantic representations within large language models (LLMs) faces a fundamental challenge: the inherent asymmetry of natural languages. Different languages exhibit vast disparities in syntactic structures, lexical choices, and cultural nuances, making the creation of a truly shared, symmetric embedding space a non-trivial task. This paper aims to address this critical problem by introducing a novel framework to forge robust and symmetric multilingual sentence embeddings. Our approach, named DACL (Dynamic Asymmetric Contrastive Learning), is anchored in two powerful asymmetric learning paradigms: Contrastive Learning and Dynamic Curriculum Learning (DCL). We extend Contrastive Learning to the multilingual context, where it asymmetrically treats semantically equivalent sentences from different languages (positive pairs) and sentences with distinct meanings (negative pairs) to enforce semantic symmetry in the target embedding space. To further refine this process, we incorporate Dynamic Curriculum Learning, which introduces a second layer of asymmetry by dynamically scheduling training instances from easy to hard. This dual-asymmetric strategy enables the model to progressively master complex cross-lingual relationships, starting with more obvious semantic equivalences and advancing to subtler ones. Our comprehensive experiments on benchmark cross-lingual tasks, including sentence retrieval and cross-lingual classification (XNLI, PAWS-X, MLDoc, MARC), demonstrate that DACL significantly outperforms a wide range of established baselines. The results validate our dual-asymmetric framework as a highly effective approach for forging robust multilingual embeddings, particularly excelling in tasks involving complex linguistic asymmetries. Ultimately, this work contributes a novel dual-asymmetric learning framework that effectively leverages linguistic asymmetry to achieve robust semantic symmetry across languages. It offers valuable insights for developing more capable, fair, and interpretable multilingual LLMs, emphasizing that deliberately leveraging asymmetry in the learning process is a highly effective strategy.<\/jats:p>","DOI":"10.3390\/sym17091386","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T06:25:57Z","timestamp":1756189557000},"page":"1386","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Resolving Linguistic Asymmetry: Forging Symmetric Multilingual Embeddings Through Asymmetric Contrastive and Curriculum Learning"],"prefix":"10.3390","volume":"17","author":[{"given":"Lei","family":"Meng","sequence":"first","affiliation":[{"name":"College of Information Engineering, Xuchang University, Xuchang 461000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3401-1771","authenticated-orcid":false,"given":"Yinlin","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, No. 95 Zhongguancun East Road, Beijing 100100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Science and Electrical Engineering, Beihang University, Beijing 100190, China"},{"name":"Wuhan Second Ship Design and Research Institute, Wuhan 430000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caipei","family":"Yang","sequence":"additional","affiliation":[{"name":"Wuhan Second Ship Design and Research Institute, Wuhan 430000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kvapil\u00edkov\u00e1, I., Artetxe, M., Labaka, G., Agirre, E., and Bojar, O. (2020, January 5\u201310). Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, Online.","DOI":"10.18653\/v1\/2020.acl-srw.34"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Cai, D., Li, X., Ho, J.C.S., Bing, L., and Lam, W. (2022, January 7\u201311). Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates.","DOI":"10.18653\/v1\/2022.emnlp-main.433"},{"key":"ref_3","first-page":"14074","article-title":"An ensemble distillation framework for sentence embeddings with multilingual round-trip translation","volume":"37","author":"Zong","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1162\/tacl_a_00288","article-title":"Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond","volume":"7","author":"Artetxe","year":"2019","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhu, S., Mi, C., and Zhang, L. (2021, January 14\u201316). Inducing Bilingual Word Representations for Non-isomorphic Spaces by an Unsupervised Way. Proceedings of the International Conference on Knowledge Science, Engineering and Management, Tokyo, Japan.","DOI":"10.1007\/978-3-030-82136-4_37"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1007\/s10590-021-09274-0","article-title":"Improving bilingual word embeddings mapping with monolingual context information","volume":"35","author":"Zhu","year":"2021","journal-title":"Mach. Transl."},{"key":"ref_7","unstructured":"Pires, T., Schlinger, E., and Garrette, D. (August, January 28). How Multilingual is Multilingual BERT?. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzm\u00e1n, F., Grave, \u00c9., Ott, M., Zettlemoyer, L., and Stoyanov, V. (2020, January 5\u201310). Unsupervised Cross-lingual Representation Learning at Scale. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online.","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref_9","unstructured":"Mullov, C. (2020). Unsupervised Transfer Learning in Multilingual Neural Machine Translation with Cross-Lingual Word Embeddings. [Ph.D. Thesis, Karlsruhe Institute of Technology]."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Feng, F., Yang, Y., Cer, D., Arivazhagan, N., and Wang, W. (2022, January 22\u201327). Language-agnostic BERT Sentence Embedding. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland.","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"ref_11","unstructured":"Zhu, S., Xu, S., Sun, H., Pan, L., Cui, M., Du, J., Jin, R., Branco, A., and Xiong, D. (2024). Multilingual Large Language Models: A Systematic Survey. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chanchani, S., and Huang, R. (2023, January 9\u201314). Composition-contrastive Learning for Sentence Embeddings. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.acl-long.882"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Reimers, N., and Gurevych, I. (2020, January 16\u201320). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Chidambaram, M., Yang, Y., Cer, D., Yuan, S., Sung, Y., Strope, B., and Kurzweil, R. (2019, January 2). Learning Cross-Lingual Sentence Representations via a Multi-task Dual-Encoder Model. Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), Florence, Italy.","DOI":"10.18653\/v1\/W19-4330"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, T., Ye, W., Yang, B., Zhang, L., Ren, X., Liu, D., Sun, J., Zhang, S., Zhang, H., and Zhao, W. (2022, January 12\u201317). Frequency-aware contrastive learning for neural machine translation. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.","DOI":"10.1609\/aaai.v36i10.21426"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Pan, X., Wang, M., Wu, L., and Li, L. (2021, January 1\u20136). Contrastive Learning for Many-to-many Multilingual Neural Machine Translation. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Online.","DOI":"10.18653\/v1\/2021.acl-long.21"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhu, S., Mi, C., and Shi, X. (2021, January 23\u201325). An explainable evaluation of unsupervised transfer learning for parallel sentences mining. Proceedings of the Web and Big Data: 5th International Joint Conference, APWeb-WAIM 2021, Guangzhou, China. Proceedings, Part I 5.","DOI":"10.1007\/978-3-030-85896-4_22"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Platanios, E.A., Stretcu, O., Neubig, G., Poczos, B., and Mitchell, T. (2019, January 2\u20137). Competence-based Curriculum Learning for Neural Machine Translation. Proceedings of the 2019 Conference of the North. Association for Computational Linguistics, Minneapolis, MN, USA.","DOI":"10.18653\/v1\/N19-1119"},{"key":"ref_19","unstructured":"Zhu, S., Li, X., Yang, Y., Wang, L., and Mi, C. (2017, January 8\u201312). Learning Bilingual Lexicon for Low-Resource Language Pairs. Proceedings of the Natural Language Processing and Chinese Computing: 6th CCF International Conference, NLPCC 2017, Dalian, China. Proceedings 6."},{"key":"ref_20","first-page":"1","article-title":"Unsupervised parallel sentences of machine translation for Asian language pairs","volume":"22","author":"Zhu","year":"2023","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"ref_21","unstructured":"Chowdhury, S., Baili, N., and Vannah, B. (2021, January 10\u201311). Ensemble Fine-tuned mBERT for Translation Quality Estimation. Proceedings of the Sixth Conference on Machine Translation, Punta Cana, Dominican Republic."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Xu, Y., Hu, L., Zhao, J., Qiu, Z., Xu, K., Ye, Y., and Gu, H. (2025). A survey on multilingual large language models: Corpora, alignment, and bias. Front. Comput. Sci., 19.","DOI":"10.1007\/s11704-024-40579-4"},{"key":"ref_23","unstructured":"Al-Onaizan, Y., Bansal, M., and Chen, Y.N. (2024, January 12\u201316). Representational Isomorphism and Alignment of Multilingual Large Language Models. Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, FL, USA."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"110381","DOI":"10.1016\/j.knosys.2023.110381","article-title":"CLSEP: Contrastive learning of sentence embedding with prompt","volume":"266","author":"Wang","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhang, M., Mosbach, M., Adelani, D., Hedderich, M., and Klakow, D. (2022, January 10\u201315). MCSE: Multimodal Contrastive Learning of Sentence Embeddings. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, WA, USA.","DOI":"10.18653\/v1\/2022.naacl-main.436"},{"key":"ref_26","first-page":"8635","article-title":"Learning a few-shot embedding model with contrastive learning","volume":"35","author":"Liu","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, H., Liu, Z., Yang, L., and Yu, P.S. (2022, January 17\u201321). Contrastvae: Contrastive variational autoencoder for sequential recommendation. Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA.","DOI":"10.1145\/3511808.3557268"},{"key":"ref_28","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"Gan","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_29","unstructured":"Zhu, S., Cui, M., and Xiong, D. (2024, January 20\u201325). Towards robust in-context learning for machine translation with large language models. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-cOLING 2024), Torino, Italy."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, G., Hou, L., Chen, Y., Dai, W., Shang, L., Jiang, X., Liu, Q., Pan, J., and Wang, W. (2023, January 9\u201314). mclip: Multilingual clip via cross-lingual transfer. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, ON, Canada.","DOI":"10.18653\/v1\/2023.acl-long.728"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., and Weston, J. (2009, January 14\u201318). Curriculum learning. Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, QC, Canada.","DOI":"10.1145\/1553374.1553380"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wang, Y., Hou, H., Sun, S., Wu, N., Jian, W., Yang, Z., and Wang, P. (2022, January 6\u201310). Dynamic Mask Curriculum Learning for Non-Autoregressive Neural Machine Translation. Proceedings of the China Conference on Machine Translation, Lhasa, China.","DOI":"10.1007\/978-981-19-7960-6_8"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhu, S., Pan, L., Li, B., and Xiong, D. (2024, January 11\u201316). LANDeRMT: Dectecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Bangkok, Thailand.","DOI":"10.18653\/v1\/2024.acl-long.656"},{"key":"ref_34","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13\u201318). A simple framework for contrastive learning of visual representations. Proceedings of the International Conference on Machine Learning, PmLR, Vienna, Austria."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Wei, J., and Zou, K. (2019, January 3\u20137). EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1670"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Conneau, A., Rinott, R., Lample, G., Williams, A., Bowman, S., Schwenk, H., and Stoyanov, V. (November, January 31). XNLI: Evaluating Cross-lingual Sentence Representations. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium.","DOI":"10.18653\/v1\/D18-1269"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yang, Y., Zhang, Y., Tar, C., and Baldridge, J. (2019, January 3\u20137). PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1382"},{"key":"ref_38","unstructured":"Schwenk, H., and Li, X. (2018, January 7\u201312). A Corpus for Multilingual Document Classification in Eight Languages. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Keung, P., Lu, Y., Szarvas, G., and Smith, N.A. (2020, January 16\u201320). The Multilingual Amazon Reviews Corpus. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.","DOI":"10.18653\/v1\/2020.emnlp-main.369"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Liang, Y., Duan, N., Gong, Y., Wu, N., Guo, F., Qi, W., Gong, M., Shou, L., Jiang, D., and Cao, G. (2020, January 16\u201320). XGLUE: A New Benchmark Datasetfor Cross-lingual Pre-training, Understanding and Generation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.","DOI":"10.18653\/v1\/2020.emnlp-main.484"},{"key":"ref_41","first-page":"16857","article-title":"Mpnet: Masked and permuted pre-training for language understanding","volume":"33","author":"Song","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_42","unstructured":"Wang, L., Yang, N., Huang, X., Jiao, B., Yang, L., Jiang, D., Majumder, R., and Wei, F. (2022). Text embeddings by weakly-supervised contrastive pre-training. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., and Liu, Z. (2024). Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.137"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/9\/1386\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:32:20Z","timestamp":1760034740000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/9\/1386"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":43,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["sym17091386"],"URL":"https:\/\/doi.org\/10.3390\/sym17091386","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,25]]}}}