Elamur Research⌕
☰
home / papers / 2026 / Push and Pull: Training Sentence Encoders with Contrastive Losses for Distance-Based Multi-Label Text Classification

Push and Pull: Training Sentence Encoders with Contrastive Losses for Distance-Based Multi-Label Text Classification

Summary

Distance-based classification (DBC) decides whether a label fits a text by comparing their embeddings with cosine similarity. This makes it cheap and easy to extend to new labels. However, it is rarely used for multi-label text classification (MLTC), where several labels per text require similarity thresholds. Earlier work introduced label-specific thresholds. The authors build on it by fine-tuning sentence encoders with supervised contrastive objectives, which pull a text toward its correct label embeddings and push it away from wrong ones. They compare three such losses on three English encoders (Stella, GIST-Large, BGE) and one Dutch encoder (BERTje-nli). The datasets are SemEval, BioTech, Reuters, AAPD, LitCovid and two label levels of the Dutch EventDNA corpus. To mimic scarce annotation, only the validation splits are used for training. Contrastive fine-tuning beats the untuned encoders on every dataset. The resulting models come close to, or match, fine-tuned BERT-style classifiers and zero-/few-shot LLMs. This matters for teams that need lightweight, adaptable multi-label classifiers with little labelled data, including for languages other than English.

Key points

  • Three losses are compared: Label Margin Loss (L_LM), L_TM, and a pairwise margin loss L_P. GLMM significance tests (Holm-Bonferroni corrected) show that all three beat the base encoders. L_P is significantly better than the other two in every dataset–model combination tested.
  • On LitCovid, L_P raises Stella's micro-F1 from 61.68 to 88.01. This is roughly on par with RoBERTa (88.20) and far above Qwen3:14b (66.31).
  • On SemEval, L_P raises Stella's micro-F1 from 48.96 to 66.83 and its macro-F1 from 41.20 to 57.20. The macro-F1 exceeds both Qwen3:14b (48.97) and RoBERTa (53.83).
  • All encoders have under 1B parameters (Stella 435M, GIST-Large 335M, BGE 109M, BERTje-nli 110M) and fit on a single 11GB RTX 2080 Ti.
  • Data preparation:
    • AAPD, LitCovid and EventDNA received stratified splits.
    • AAPD abbreviations were mapped to descriptive arXiv category names.
    • EventDNA labels were translated into Dutch; its bottom level has 494 labels.
    • The code is released at github.com/clips/push_and_pull.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/4fiaod5mcdsr

@inproceedings{nooten2026push,
  title = {{Push and Pull: Training Sentence Encoders with Contrastive Losses for Distance-Based Multi-Label Text Classification}},
  author = {Nooten, Jens Van and Kosar, Andriy},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/4fiaod5mcdsr},
  url = {https://doi.org/10.63317/4fiaod5mcdsr}
}

References

97 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Silvana Abdi, Mahrokh Hassani, Rosalien Kinds, Timo Strijbis, and Roman Terpstra. 2025. HalluRAG-RUG at SemEval-2025 task 3: Using retrieval-augmented generation for hallucination detection in model outputs. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pag… find
  2. Bang An, Shiyue Zhang, and Mark Dredze. 2025. RAG LLMs are not safer: A safety analysis of retrieval-augmented generation for large language models. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technolog… find
  3. Chidanand Apt’e, Fred Damerau, and Sholom M. Weiss. 1994. Automated learning of decision rules for text categorization. ACM Transactions on Information Systems. To appear. find
  4. Alexandre Audibert, Aurélien Gauffre, and Massih-Reza Amini. 2025. Multi-label contrastive learning : A comprehensive study. find
  5. Emanuel Ben-Baruch, Tal Ridnik, Nadav Zamir, Asaf Noy, Itamar Friedman, Matan Protter, and Lihi Zelnik-Manor. 2021. Asymmetric loss for multi-label classification. find
  6. Jasmin Bogatinovski, Ljupčo Todorovski, Sašo Džeroski, and Dragi Kocev. 2022. Comprehensive comparative study of multi-label classification methods. Expert Systems with Applications, 203:117215. find
  7. Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. find
  8. Martin Juan José Bucher and Marco Martini. 2024. Fine-tuned ’small’ llms (still) significantly outperform zero-shot generative ai models in text classification. find
  9. Xunxin Cai, Meng Xiao, Zhiyuan Ning, and Yuanchun Zhou. 2023. Resolving the imbalance issue in hierarchical disciplinary topic inference via llm-based data augmentation. In 2023 IEEE International Conference on Data Mining Workshops (ICDMW), pages 1424–1429. find
  10. Ming-Wei Chang, Lev Ratinov, Dan Roth, and Vivek Srikumar. 2008. Importance of semantic representation: dataless classification. In Proceedings of the 23rd National Conference on Artificial Intelligence - Volume 2, AAAI’08, page 830–835. AAAI Press. find
  11. Qingyu Chen, Alexis Allot, and Zhiyong Lu. 2020. LitCovid: an open database of COVID-19 literature. Nucleic Acids Research, 49(D1):D1534– D1540. find
  12. Camiel Colruyt, Orphée De Clercq, Thierry Desot, and Veronique Hoste. 2022. Eventdna: a dataset for dutch news event extraction as a basis for news diversification. Language Resources and Evaluation, 57:189 – 221. find
  13. Pieter Delobelle, Thomas Winters, and Bettina Berendt. 2020. Robbert: a dutch roberta-based language model. find our card
  14. Jiawen Deng and Fuji Ren. 2023. Multi-label emotion detection via emotion-specified feature extraction and emotion correlation learning. IEEE Transactions on Affective Computing, 14(1):475– 486. find
  15. Emre Deniz, Hasan Erbay, and Mustafa Coşar. 2022. Multi-label classification of e-commerce customer reviews via machine learning. Axioms, 11(9). find
  16. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  17. Qingwu Fan and Changsheng Qiu. 2023. Hierarchical multi-label text classification method based on multi-level decoupling. In 2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE), pages 453–457. find
  18. Eva Gibaja and Sebastián Ventura. 2014. Multi-label learning: a review of the state of the art and ongoing research. WIREs Data Mining and Knowledge Discovery, 4(6):411–444. find
  19. A. F. Giraldo-Forero, J. A. Jaramillo-Garzón, and C. G. Castellanos-Domínguez. 2013. A comparison of multi-label techniques based on problem transformation for protein functional prediction. In 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC),… find
  20. Rohit Gupta, Mamshad Nayeem Rizve, Jayakrishnan Unnikrishnan, Ashish Tawari, Son Tran, Mubarak Shah, Benjamin Yao, and Trishul Chilimbi. 2024. Open vocabulary multi-label video classification. find
  21. Mohammadreza Heydarian, Thomas E. Doyle, and Reza Samavi. 2022. Mlcm: Multi-label confusion matrix. IEEE Access, 10:19083–19095. find
  22. Haigen Hu, Xiaoyuan Wang, Yan Zhang, Qi Chen, and Qiu Guan. 2024. A comprehensive survey on contrastive learning. Neurocomputing, 610:128645. find
  23. Shan Huang, Wenlong Hu, Bin Lu, Qiang Fan, Xinyao Xu, Xiaolei Zhou, and Hao Yan. 2024. Application of label correlation in multi-label classification: A survey. Applied Sciences, 14(19). find
  24. Shu Huang, Wei Peng, Jingxuan Li, and Dongwon Lee. 2013. Sentiment and topic analysis on social media: a multi-task multi-label classification approach. In Proceedings of the 5th Annual ACM Web Science Conference, WebSci ’13, page 172–181, New York, NY, USA. Association for Computing Machinery. find
  25. Nikmah Isnaini, Adiwijaya, Mohamad Syahrul Mubarok, and Muhammad Yuslan Abu Bakar. 2019. A multi-label classification on topics of indonesian news using k-nearest neighbor. Journal of Physics: Conference Series, 1192(1):012027. find
  26. Ling Jia, Jin Fan, Dong Sun, Qingwei Gao, and Yixiang Lu. 2022. Research on multi-label classification problems based on neural networks and label correlation. In 2022 41st Chinese Control Conference (CCC), pages 7298–7302. find
  27. Andriy Kosar, Guy De Pauw, and Walter Daelemans. 2022. Unsupervised text classification with neural word embeddings. Computational Linguistics in the Netherlands Journal, 12:165–181. find
  28. Andriy Kosar, Guy De Pauw, and Walter Daelemans. 2023. Advancing topical text classification: A novel distance-based method with contextual embeddings. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 586–597, Varna, Bulgaria. INCOMA Ltd.,… find
  29. Sean Lee, Aamir Shakir, Darius Koenig, and Julius Lipp. 2024. Open source strikes bread - new fluffy embeddings model. find
  30. Jens Lemmens, Tess Dejaeghere, Tim Kreutz, Jens Van Nooten, Ilia Markov, and Walter Daelemans. 2021. Vaccinpraat: Monitoring vaccine skepticism in dutch twitter and facebook comments. Computational Linguistics in the Netherlands Journal, 11:173–188. find
  31. Qian Li, Hao Peng, Jianxin Li, Congying Xia, Renyu Yang, Lichao Sun, Philip S. Yu, and Lifang He. 2022. A survey on text classification: From traditional to deep learning. ACM Trans. Intell. Syst. Technol., 13(2). find
  32. Xiang Li, Jiexi Liu, Xinrui Wang, and Songcan Chen. 2024a. A survey on incomplete multi-label learning: Recent advances and future trends. find
  33. Xianming Li and Jing Li. 2023. Angle-optimized text embeddings. arXiv preprint arXiv:2309.12871. find
  34. Xintong Li, Jinya Jiang, Ria Dharmani, Jayanth Srinivasa, Gaowen Liu, and Jingbo Shang. 2024b. Open-world multi-label text classification with extremely weak supervision. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15084–15096, Miami, Florida, USA… find
  35. Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281. find our card
  36. Junyang Lin, Qi Su, Pengcheng Yang, Shuming Ma, and Xu Sun. 2018. Semantic-unit-based dilated convolution for multi-label text classification. CoRR, abs/1808.08561. find
  37. Nankai Lin, Guanqiu Qin, Gang Wang, Dong Zhou, and Aimin Yang. 2023. An effective deployment of contrastive learning in multi-label text classification. In Findings of the Association for Computational Linguistics: ACL 2023, pages 8730– 8744, Toronto, Canada. Association for Computational Linguistic… find
  38. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pre-training approach. find
  39. Marcus Ma, Georgios Chochlakis, Niyantha Maruthu Pandiyan, Jesse Thomason, and Shrikanth Narayanan. 2025. Large language models do multi-label classification differently. find
  40. Zhongchen Ma and Songcan Chen. 2022. A similarity-based framework for classification task. IEEE Transactions on Knowledge and Data Engineering, 35(5):5438–5443. find
  41. Usman Malik, Simon Bernard, Alexandre Pauchet, Clément Chatelain, Romain Picot-Clémente, and Jérôme Cortinovis. 2024. Pseudo-labeling with large language models for multi-label emotion classification of french tweets. IEEE Access, 12:15902–15916. find
  42. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. find
  43. Saif Mohammad, Felipe Bravo-Marquez, Mohammad Salameh, and Svetlana Kiritchenko. 2018. SemEval-2018 task 1: Affect in tweets. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 1–17, New Orleans, Louisiana. Association for Computational Linguistics. find our card
  44. Ratri Mukherjee and Kishlay Jha. 2024. Context-aware contrastive representation learning for zero-shot biomedical text classification. In Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 3611–3614, United States. IEEE. find
  45. Manjunath Mulimani and Annamaria Mesaros. 2024. Class-incremental learning for multi-label audio classification. find
  46. Ghulam Mustafa, Muhammad Usman, Lisu Yu, Muhammad Tanvir Afzal, Muhammad Sulaiman, and Abdul Shahid. 2021. Multi-label classification of research articles using word2vec and identification of similarity threshold. Scientific Reports, 11(1):21900. find
  47. Nikolaos Mylonas, Stamatis Karlos, and Grigorios Tsoumakas. 2020a. Zero-shot classification of biomedical articles with emerging mesh descriptors. In 11th Hellenic Conference on Artificial Intelligence, SETN 2020, page 175–184, New York, NY, USA. Association for Computing Machinery. find
  48. Nikolaos Mylonas, Stamatis Karlos, and Grigorios Tsoumakas. 2020b. Zero-shot classification of biomedical articles with emerging mesh descriptors. In 11th Hellenic Conference on Artificial Intelligence, SETN 2020, page 175–184, New York, NY, USA. Association for Computing Machinery. find
  49. Nobal Niraula, Samet Ayhan, Balaguruna Chidambaram, and Daniel Whyatt. 2024. Multi-label classification with generative large language models. In 2024 AIAA DATC/IEEE 43rd Digital Avionics Systems Conference (DASC), pages 1–7. find
  50. Jens Van Nooten, Andriy Kosar, Guy De Pauw, and Walter Daelemans. 2025. One size does not fit all: Exploring variable thresholds for distance-based multi-label text classification. find
  51. OpenAI. 2024. Gpt-4 technical report. find our card
  52. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. GloVe: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar. Association for Computational Linguistics. find
  53. Youri Peskine, Damir Korenčić, Ivan Grubisic, Paolo Papotti, Raphael Troncy, and Paolo Rosso. 2023. Definitions matter: Guiding GPT for multi-label classification. In The 2023 Conference on Empirical Methods in Natural Language Processing. find
  54. Clifton Poth, Hannah Sterz, Indraneil Paul, Sukannya Purkayastha, Leon Engländer, Timo Imhof, Ivan Vulić, Sebastian Ruder, Iryna Gurevych, and Jonas Pfeiffer. 2023. Adapters: A unified library for parameter-efficient and modular transfer learning. find
  55. Irina Radeva, Ivan Popchev, and Miroslava Dimitrova. 2024. Similarity thresholds in retrieval-augmented generation. In 2024 IEEE 12th International Conference on Intelligent Systems (IS), pages 1–7. find
  56. Alec Radford and Karthik Narasimhan. 2018. Improving language understanding by generative pre-training. In arxiv. find
  57. Jesse Read, Peter Reutemann, Bernhard Pfahringer, and Geoff Holmes. 2016. MEKA: A multi-label/multi-target extension to Weka. Journal of Machine Learning Research, 17(21):1–5. find
  58. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. find
  59. Tal Ridnik, Emanuel Ben-Baruch, Nadav Zamir, Asaf Noy, Itamar Friedman, Matan Protter, and Lihi Zelnik-Manor. 2021. Asymmetric loss for multi-label classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 82–91. find
  60. Prateek Veeranna Sappadla, Jinseok Nam, Eneldo Loza Mencía, and Johannes Fürnkranz. 2016. Using semantic similarity for multi-label zero-shot classification of text documents. In 24th European Symposium on Artificial Neural Networks, ESANN 2016, Bruges, Belgium, April 27-29, 2016. find
  61. Souvika Sarkar, Dongji Feng, and Shubhra Kanti Karmaker Santu. 2022. Exploring universal sentence encoders for zero-shot text classification. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference… find
  62. Souvika Sarkar, Dongji Feng, and Shubhra Kanti Karmaker Santu. 2023. Zero-shot multi-label topic inference with sentence encoders and LLMs. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 16218–16233, Singapore. Association for Computational Linguisti… find
  63. Tim Schopf, Daniel Braun, and Florian Matthes. 2023. Evaluating unsupervised text classification: Zero-shot and similarity-based approaches. In 2022 6th International Conference on Natural Language Processing and Information Retrieval (NLPIR), NLPIR 2022, New York, NY, USA. Association for Computing… find
  64. Konstantinos Sechidis, Grigorios Tsoumakas, and Ioannis Vlahavas. 2011. On the stratification of multi-label data. In Machine Learning and Knowledge Discovery in Databases, pages 145–158, Berlin, Heidelberg. Springer Berlin Heidelberg. find
  65. Aivin V. Solatorio. 2024. Gistembed: Guided in-sample selection of training negatives for text embedding fine-tuning. arXiv preprint arXiv:2402.16829. — [arXiv:2402.16829](https://arxiv.org/abs/2402.16829) find
  66. Dezhao Song, Andrew Vold, Kanika Madan, and Frank Schilder. 2022. Multi-label legal document classification: A deep learning-based approach with label-attention and domain-specific pre-training. Information Systems, 106:101718. find
  67. Hwanjun Song, Minseok Kim, and Jae-Gil Lee. 2023. Toward robustness in multi-label classification: A data augmentation strategy against imbalance and noise. find
  68. Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. Mpnet: Masked and permuted pre-training for language understanding. find our card
  69. Yangqiu Song and Dan Roth. 2014. On dataless hierarchical text classification. In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, AAAI’14, page 1579–1585. AAAI Press. find
  70. Yangqiu Song, Shyam Upadhyay, Haoruo Peng, and Dan Roth. 2016. Cross-lingual dataless classification for many languages. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI’16, page 2901–2907. AAAI Press. find
  71. Balázs Szalkai and Vince Grolmusz. 2018. Near perfect protein multi-label classification with deep neural networks. Methods, 132:50–56. Comparison and Visualization Methods for High-Dimensional Biological Data. find
  72. Adane Nega Tarekegn, Mario Giacobini, and Krzysztof Michalak. 2021. A review of methods for imbalanced multi-label classification. Pattern Recognition, 118:107965. find
  73. Adane Nega Tarekegn, Mohib Ullah, and Faouzi Alaya Cheikh. 2024. Deep learning for multi-label learning: A comprehensive survey. find
  74. Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, and Garrett Tanzer. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. find our card
  75. Gemma Team. 2025. Gemma 3 technical report. find
  76. Simon Chi Lok U, Jie He, Víctor Gutiérrez-Basulto, and Jeff Z. Pan. 2023. Instances and labels: Hierarchy-aware joint supervised contrastive learning for hierarchical multi-label text classification. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8858– 8875, Singapor… find
  77. Jens Van Nooten and Walter Daelemans. 2023. Improving Dutch vaccine hesitancy monitoring via multi-label data augmentation with GPT-3.5. In Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, pages 251–270, Toronto, Canada. Association fo… find
  78. Jens Van Nooten and Walter Daelemans. 2025. Jump to hyperspace: Comparing Euclidean and hyperbolic loss functions for hierarchical multi-label text classification. In Proceedings of the 31st International Conference on Computational Linguistics, pages 4260–4273, Abu Dhabi, UAE. Association for Compu… find
  79. Jens Van Nooten and Andriy Kosar. 2024. Advancing CSR theme and topic classification: LLMs and training enhancement insights. In Proceedings of the Joint Workshop of the 7th Financial Technology and Natural Language Processing, the 5th Knowledge Discovery from Unstructured Data in Financial Services… find
  80. Josefien Van Olmen, Jens Van Nooten, Hilde Philips, Annet Sollie, and Walter Daelemans. 2022. Predicting covid-19 symptoms from free text in medical records using artificial intelligence: Feasibility study. JMIR Med Inform, 10(4):e37771. find
  81. Bram Vanroy. 2024a. Fietje: An open, efficient llm for dutch. find
  82. Bram Vanroy. 2024b. Geitje 7b ultra: A conversational model for dutch. find
  83. Sai Pavan Kumar Veeranki, Akhila Abdulnazar, Diether Kramer, Markus Kreuzthaler, and David Benjamin Lumenta. 2024. Multi-label text classification via secondary use of large clinical real-world data sets. Scientific Reports, 14(1):26972. find
  84. Sappadla Prateek Veeranna, Jinseok Nam, Eneldo Loza Mencıa, and Johannes Fürnkranz. 2016. Using semantic similarity for multi-label zero-shot classification of text documents. In Proceeding of european symposium on artificial neural networks, computational intelligence and machine learning. bruges,… find
  85. Fengjun Wang, Moran Beladev, Ofri Kleinfeld, Elina Frayerman, Tal Shachar, Eran Fainman, Karen Lastmann Assaraf, Sarai Mizrachi, and Benjamin Wang. 2023. Text2Topic: Multi-label text classification system for efficient topic detection in user generated content with zero-shot capabilities. In Proceed… find
  86. Qian Wang, Ning Jia, and Toby P. Breckon. 2019. A baseline for multi-label image classification using an ensemble of deep convolutional neural networks. In 2019 IEEE International Conference on Image Processing (ICIP), pages 644–648. find
  87. Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff, Defu Lian, and Jian-Yun Nie. 2024. C-pack: Packaged resources to advance general chinese embedding. find
  88. Changzhen Xiong and Yanmei Shan. 2018. Subject features and hash codes for multi-label image retrieval. In 2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS), pages 808–812. find
  89. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jing Zhou, Jin… find our card
  90. Pengcheng Yang, Xu Sun, Wei Li, Shuming Ma, Wei Wu, and Houfeng Wang. 2018. SGM: Sequence generation model for multi-label classification. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3915–3926, Santa Fe, New Mexico, USA. Association for Computational Lingu… find our card
  91. Kai Yin, Chengkai Liu, Ali Mostafavi, and Xia Hu. 2024. Crisissense-llm: Instruction fine-tuned large language model for multi-label social media text classification in disaster informatics. find
  92. Min-Ling Zhang, Yu-Kun Li, Xu-Ying Liu, and Xin Geng. 2018. Binary relevance for multi-label learning: an overview. Frontiers of Computer Science, 12(2):191–202. find
  93. Min-Ling Zhang and Zhi-Hua Zhou. 2014. A review on multi-label learning algorithms. IEEE Transactions on Knowledge and Data Engineering, 26(8):1819–1837. find
  94. Pingyue Zhang and Mengyue Wu. 2024. Multi-label supervised contrastive learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(15):16786–16793. find
  95. Rui Zhang, Yangfeng Ji, Yue Zhang, and Rebecca J. Passonneau. 2022a. Contrastive data and learning for natural language processing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorial Abstracts, p… find
  96. Shu Zhang, Ran Xu, Caiming Xiong, and Chetan Ramaiah. 2022b. Use all the labels: A hierarchical multi-label contrastive learning framework. find
  97. Kaitlyn Zhou, Kawin Ethayarajh, Dallas Card, and Dan Jurafsky. 2022. Problems with cosine as a measure of embedding similarity for high frequency words. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/nooten-2026-push-pull-training-sentence-encoders/