Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
95 tokens/sec
Gemini 2.5 Pro Premium
32 tokens/sec
GPT-5 Medium
18 tokens/sec
GPT-5 High Premium
20 tokens/sec
GPT-4o
97 tokens/sec
DeepSeek R1 via Azure Premium
87 tokens/sec
GPT OSS 120B via Groq Premium
468 tokens/sec
Kimi K2 via Groq Premium
202 tokens/sec
2000 character limit reached

Cross-lingual Lifelong Learning (2205.11152v2)

Published 23 May 2022 in cs.CL

Abstract: The longstanding goal of multi-lingual learning has been to develop a universal cross-lingual model that can withstand the changes in multi-lingual data distributions. There has been a large amount of work to adapt such multi-lingual models to unseen target languages. However, the majority of work in this direction focuses on the standard one-hop transfer learning pipeline from source to target languages, whereas in realistic scenarios, new languages can be incorporated at any time in a sequential manner. In this paper, we present a principled Cross-lingual Continual Learning (CCL) evaluation paradigm, where we analyze different categories of approaches used to continually adapt to emerging data from different languages. We provide insights into what makes multilingual sequential learning particularly challenging. To surmount such challenges, we benchmark a representative set of cross-lingual continual learning algorithms and analyze their knowledge preservation, accumulation, and generalization capabilities compared to baselines on carefully curated datastreams. The implications of this analysis include a recipe for how to measure and balance different cross-lingual continual learning desiderata, which go beyond conventional transfer learning.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Knowledge distillation from internal representations. In The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA, February 7-12, 2020, pages 7350–7357. AAAI Press.
  2. On the cross-lingual transferability of monolingual representations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4623–4637, Online. Association for Computational Linguistics.
  3. Continual lifelong learning in natural language processing: A survey. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6523–6541, Barcelona, Spain (Online). International Committee on Computational Linguistics.
  4. Multi-lingual intent detection and slot filling in a joint bert-based model. ArXiv preprint, abs/1907.02884.
  5. Efficient lifelong learning with A-GEM. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net.
  6. Continual learning with tiny episodic memories. ArXiv preprint, abs/1902.10486.
  7. Unsupervised cross-lingual representation learning at scale. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8440–8451, Online. Association for Computational Linguistics.
  8. XNLI: Evaluating cross-lingual sentence representations. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2475–2485, Brussels, Belgium. Association for Computational Linguistics.
  9. Episodic memory in lifelong language learning. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 13122–13131.
  10. 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, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
  11. Towards continual learning for multilingual machine translation via vocabulary substitution. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1184–1192, Online. Association for Computational Linguistics.
  12. More data, more relations, more context and more openness: A review and outlook for relation extraction. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 745–758, Suzhou, China. Association for Computational Linguistics.
  13. Avijit Hazra. 2017. Using the confidence interval confidently. Journal of Thoracic Disease, 9(10):4124–4129.
  14. Distilling the knowledge in a neural network. ArXiv preprint, abs/1503.02531.
  15. Lifelong pretraining: Continually adapting language models to emerging corpora. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4764–4780, Seattle, United States. Association for Computational Linguistics.
  16. The state and fate of linguistic diversity and inclusion in the NLP world. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6282–6293, Online. Association for Computational Linguistics.
  17. Mahendra Kariya. 2018. Dark knowledge in neural networks. Accessed on March 7th, 2023.
  18. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
  19. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences, 114(13):3521–3526.
  20. Philipp Koehn. 2004. Statistical significance tests for machine translation evaluation. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pages 388–395, Barcelona, Spain. Association for Computational Linguistics.
  21. MLQA: Evaluating cross-lingual extractive question answering. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7315–7330, Online. Association for Computational Linguistics.
  22. MTOP: A comprehensive multilingual task-oriented semantic parsing benchmark. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 2950–2962, Online. Association for Computational Linguistics.
  23. Zhizhong Li and Derek Hoiem. 2016. Learning without forgetting. In Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part IV, volume 9908 of Lecture Notes in Computer Science, pages 614–629. Springer.
  24. Preserving cross-linguality of pre-trained models via continual learning. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 64–71, Online. Association for Computational Linguistics.
  25. David Lopez-Paz and Marc’Aurelio Ranzato. 2017. Gradient episodic memory for continual learning. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 6467–6476.
  26. Continual learning in task-oriented dialogue systems. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7452–7467, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  27. Michael McCloskey and Neal J. Cohen. 1989. Catastrophic interference in connectionist networks: The sequential learning problem. In Gordon H. Bower, editor, Psychology of Learning and Motivation, volume 24, pages 109–165. Academic Press.
  28. The stability-plasticity dilemma: Investigating the continuum from catastrophic forgetting to age-limited learning effects. Frontiers in psychology, 4:504.
  29. X-METRA-ADA: Cross-lingual meta-transfer learning adaptation to natural language understanding and question answering. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3617–3632, Online. Association for Computational Linguistics.
  30. WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3992–4006, Seattle, United States. Association for Computational Linguistics.
  31. When being unseen from mBERT is just the beginning: Handling new languages with multilingual language models. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 448–462, Online. Association for Computational Linguistics.
  32. Lifting the curse of multilinguality by pre-training modular transformers. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3479–3495, Seattle, United States. Association for Computational Linguistics.
  33. AdapterHub: A framework for adapting transformers. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 46–54, Online. Association for Computational Linguistics.
  34. MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7654–7673, Online. Association for Computational Linguistics.
  35. UNKs everywhere: Adapting multilingual language models to new scripts. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10186–10203, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
  36. Online structured laplace approximations for overcoming catastrophic forgetting. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, pages 3742–3752.
  37. Transfer learning in natural language processing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials, pages 15–18, Minneapolis, Minnesota. Association for Computational Linguistics.
  38. Continual learning with deep generative replay. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 2990–2999.
  39. LAMOL: language modeling for lifelong language learning. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net.
  40. Three types of incremental learning. Nature Machine Intelligence, 4(12):1185–1197.
  41. Attention is all you need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 5998–6008.
  42. PAWS-X: A cross-lingual adversarial dataset for paraphrase identification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3687–3692, Hong Kong, China. Association for Computational Linguistics.
  43. Continual learning through synaptic intelligence. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, volume 70 of Proceedings of Machine Learning Research, pages 3987–3995. PMLR.
Citations (7)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now