{"type":"ScholarlyArticle","title":"Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching","authors":[{"name":"Zhuoran Li","slug":"zhuoran-li","given":"Zhuoran","family":"Li","affiliation":"SKLSDE , School of Computer Science and Engineering , Beihang University , Beijing , China"},{"name":"Chunming Hu","slug":"chunming-hu","given":"Chunming","family":"Hu","affiliation":"SKLSDE , School of Computer Science and Engineering , Beihang University , Beijing , China; School of Software , Beihang University , Beijing , China"},{"name":"Junfan Chen","slug":"junfan-chen","given":"Junfan","family":"Chen","affiliation":"SKLSDE , School of Computer Science and Engineering , Beihang University , Beijing , China; School of Software , Beihang University , Beijing , China"},{"name":"Zhijun Chen","slug":"zhijun-chen","given":"Zhijun","family":"Chen","affiliation":"SKLSDE , School of Computer Science and Engineering , Beihang University , Beijing , China"},{"name":"Xiaohui Guo","slug":"xiaohui-guo","given":"Xiaohui","family":"Guo","affiliation":"Hangzhou Innovation Institute , Beihang University , Hangzhou , China"},{"name":"Richong Zhang","slug":"richong-zhang","given":"Richong","family":"Zhang","affiliation":"SKLSDE , School of Computer Science and Engineering , Beihang University , Beijing , China"}],"abstract":"Code-switching is a data augmentation scheme mixing words from multiple languages into source lingual text. It has achieved considerable generalization performance of cross-lingual transfer tasks by aligning cross-lingual contextual word representations. However, uncontrolled and over-replaced code-switching would augment dirty samples to model training. In other words, the excessive code-switching text samples will negatively hurt the models' cross-lingual transferability. To this end, we propose a Progressive Code-Switching (PCS) method to gradually generate moderately difficult code-switching examples for the model to discriminate from easy to hard. The idea is to incorporate progressively the preceding learned multilingual knowledge using easier code-switching data to guide model optimization on succeeding harder code-switching data. Specifically, we first design a difficulty measurer to measure the impact of replacing each word in a sentence based on the word relevance score. Then a code-switcher generates the code-switching data of increasing difficulty via a controllable temperature variable. In addition, a training scheduler decides when to sample harder code-switching data for model training. Experiments show our model achieves state-of-the-art results on three different zero-shot cross-lingual transfer tasks across ten languages.","doi":"10.24963/ijcai.2024/706","url":"https://ijcai.org/proceedings/2024/706","pdf":"https://ijcai.org/proceedings/2024/0706.pdf","markdown":"https://ijcai.org/proceedings/2024/706.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/706","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Natural Language Processing","track":"Main Track","number":706,"pages":{"first":6388,"last":6396},"keywords":["Natural Language Processing: NLP: Applications","Natural Language Processing: NLP: Machine translation and multilinguality"],"videos":[],"references":[{"position":1,"raw":"[Arras et al., 2019] Leila Arras, Ahmed Osman, Klaus- Robert Müller, and Wojciech Samek. Evaluating recurrent neural network explanations. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, 2019.","title":"Evaluating recurrent neural network explanations","authors":"Leila Arras, Ahmed Osman, Klaus-Robert Müller, Wojciech Samek","year":"2019","venue":"Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Artetxe and Schwenk, 2019] Mikel Artetxe and Holger Schwenk. Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond. Trans- actions of the Association for Computational Linguistics, 2019.","title":"Massively multilingual sentence embeddings for zero-shot cross-lingual transfer and beyond","authors":"Artetxe, Schwenk, Mikel Artetxe, Holger Schwenk","year":"2019","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bach et al., 2015] Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one, 2015.","title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","authors":"Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, Wojciech Samek","year":"2015","venue":"PloS one","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bengio et al., 2009] Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. Curriculum learning. In Proc. of ICML, 2009.","title":"Curriculum learning","authors":"Yoshua Bengio, Jérôme Louradour, Ronan Collobert, Jason Weston","year":"2009","venue":"Proc. of ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cao et al., 2020] Steven Cao, Nikita Kitaev, and Dan Klein. Multilingual alignment of contextual word representa- tions, 2020.","title":"Multilingual alignment of contextual word representations","authors":"Steven Cao, Nikita Kitaev, Dan Klein","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chi et al., 2021] Zewen Chi, Li Dong, Furu Wei, Nan Yang, Saksham Singhal, Wenhui Wang, Xia Song, Xian- Ling Mao, Heyan Huang, and Ming Zhou. InfoXLM: An information-theoretic framework for cross-lingual lan- guage model pre-training. In Proc. of NAACL, 2021.","title":"InfoXLM: An information-theoretic framework for cross-lingual language model pre-training","authors":"Zewen Chi, Li Dong, Furu Wei, Nan Yang, Saksham Singhal, Wenhui Wang, Xia Song, Xian-Ling Mao, Heyan Huang, Ming Zhou","year":"2021","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Conneau and Lample, 2019] Alexis Conneau and Guil- laume Lample. Cross-lingual language model pretraining. In Proc. of NeuIPS, 2019.","title":"Alexis Conneau and Guillaume Lample. Cross-lingual language model pretraining","authors":"Lample Conneau","year":"2019","venue":"Proc. of NeuIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Conneau et al., 2017] Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, and Hervé Jégou. Word translation without parallel data, 2017.","title":"Word translation without parallel data","authors":"Alexis Conneau, Guillaume Lample, Marc'aurelio Ranzato, Ludovic Denoyer, Hervé Jégou","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Conneau et al., 2020] Alexis Conneau, Kartikay Khandel- wal, Naman Goyal, Vishrav Chaudhary, Guillaume Wen- zek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. Unsupervised cross- lingual representation learning at scale. In Proc. of ACL, 2020.","title":"Unsupervised crosslingual representation learning at scale","authors":"Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, Veselin Stoyanov","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understand- ing. In Proc. of NAACL, 2019. Feng et al., 2022]","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"Yukun Feng, Feng Li, and Philipp Koehn. Toward the limitation of code-switching in cross-lingual transfer. In Proc. of EMNLP, 2022.","title":"Toward the limitation of code-switching in cross-lingual transfer","authors":"Yukun Feng, Feng Li, Philipp Koehn","year":"2022","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Goyal et al., 2021] Naman Goyal, Jingfei Du, Myle Ott, Giri Anantharaman, and Alexis Conneau. Larger-scale transformers for multilingual masked language modeling. In Proc. of RepL4NLP, 2021.","title":"Larger-scale transformers for multilingual masked language modeling","authors":"Naman Goyal, Jingfei Du, Myle Ott, Giri Anantharaman, Alexis Conneau","year":"2021","venue":"Proc. of RepL4NLP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Graves et al., 2017] Alex Graves, Marc G. Bellemare, Jacob Menick, Remi Munos, and Koray Kavukcuoglu. Auto- mated curriculum learning for neural networks, 2017.","title":"Automated curriculum learning for neural networks","authors":"Alex Graves, Marc G Bellemare, Jacob Menick, Remi Munos, Koray Kavukcuoglu","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ji et al., 2023] Yixin Ji, Jikai Wang, Juntao Li, Hai Ye, and Min Zhang. Isotropic representation can improve zero- shot cross-lingual transfer on multilingual language mod- els. In Houda Bouamor, Juan Pino, and Kalika Bali, ed- itors, Findings of the Association for Computational Lin- guistics: EMNLP 2023, pages 8104-8118, Singapore, De- cember 2023. Association for Computational Linguistics.","title":"Isotropic representation can improve zeroshot cross-lingual transfer on multilingual language models","authors":"Yixin Ji, Jikai Wang, Juntao Li, Hai Ye, Min Zhang","year":"2023","venue":"Findings of the Association for Computational Linguistics: EMNLP 2023","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kirkpatrick et al., 2017] James Kirkpatrick, Razvan Pas- canu, Neil Rabinowitz, Joel Veness, Guillaume Des- jardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al. Overcom- ing catastrophic forgetting in neural networks. Proceed- ings of the national academy of sciences, 2017.","title":"Overcoming catastrophic forgetting in neural networks","authors":"James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska","year":"2017","venue":"Proceedings of the national academy of sciences","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kumar et al., 2010] M.Pawan Kumar, Benjamin Packer, and Daphne Koller. Self-paced learning for latent variable models. In Advances in Neural Information Processing Systems, volume 23.","title":"Self-paced learning for latent variable models","authors":"M Pawan Kumar, Benjamin Packer, Daphne Koller","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"Curran Associates, Inc., 2010.","title":null,"authors":"Curran Associates, Inc","year":"2010","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Lalor and Yu, 2020] John P. Lalor and Hong Yu. Dynamic data selection for curriculum learning via ability estima- tion. In Proc. of EMNLP Findings, 2020.","title":"Dynamic data selection for curriculum learning via ability estimation","authors":"John P Lalor, Hong Yu","year":"2020","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lee et al., 2021] Dohyeon Lee, Jaeseong Lee, Gyewon Lee, Byung-gon Chun, and Seung-won Hwang. Scopa: Soft code-switching and pairwise alignment for zero-shot cross-lingual transfer. In Proc. of CIKM, 2021.","title":"Scopa: Soft code-switching and pairwise alignment for zero-shot cross-lingual transfer","authors":"Lee","year":"2021","venue":"Proc. of CIKM","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Liu et al., 2020] Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Peng Xu, and Pascale Fung. Attention-informed mixed-language training for zero-shot cross-lingual task- oriented dialogue systems. In Proc. of AAAI, 2020.","title":"Attention-informed mixed-language training for zero-shot cross-lingual taskoriented dialogue systems","authors":"Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Peng Xu, Pascale Fung","year":"2020","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Lu et al., 2023] Jinliang Lu, Yu Lu, and Jiajun Zhang. Take a closer look at multilinguality! improve multilingual pre-training using monolingual corpora only. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, pages 2891-2907, Singapore, December 2023. As- sociation for Computational Linguistics.","title":"Take a closer look at multilinguality! improve multilingual pre-training using monolingual corpora only","authors":"Lu","year":"2023","venue":"Findings of the Association for Computational Linguistics: EMNLP 2023","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ma et al., 2022] Zhanyu Ma, Jian Ye, Xurui Yang, and Jian- feng Liu. HCLD: A hierarchical framework for zero-shot cross-lingual dialogue system. In Proc. of COLING, 2022.","title":"HCLD: A hierarchical framework for zero-shot cross-lingual dialogue system","authors":"Zhanyu Ma, Jian Ye, Xurui Yang, Jianfeng Liu","year":"2022","venue":"Proc. of COLING","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Nishikawa et al., 2022] Sosuke Nishikawa, Ikuya Yamada, Yoshimasa Tsuruoka, and Isao Echizen. A multilingual bag-of-entities model for zero-shot cross-lingual text clas- sification. In Antske Fokkens and Vivek Srikumar, ed- itors, Proceedings of the 26th Conference on Computa- tional Natural Language Learning (CoNLL), pages 1-12, Abu Dhabi, United Arab Emirates (Hybrid), December 2022. Association for Computational Linguistics.","title":"A multilingual bag-of-entities model for zero-shot cross-lingual text classification","authors":"Nishikawa","year":"2022","venue":"Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Nooralahzadeh and Sennrich, 2023] Farhad Nooralahzadeh and Rico Sennrich. Improving the cross-lingual general- isation in visual question answering. In Proc. of AAAI, 2023.","title":"Improving the cross-lingual generalisation in visual question answering","authors":"Farhad Nooralahzadeh, Rico Sennrich","year":"2023","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Pan et al., 2021] Lin Pan, Chung-Wei Hang, Haode Qi, Ab- hishek Shah, Saloni Potdar, and Mo Yu. Multilingual BERT post-pretraining alignment. In Proc. of NAACL, 2021.","title":"Multilingual BERT post-pretraining alignment","authors":"Lin Pan, Chung-Wei Hang, Haode Qi, Abhishek Shah, Saloni Potdar, Mo Yu","year":"2021","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Platanios et al., 2019] Emmanouil Antonios Platanios, Otilia Stretcu, Graham Neubig, Barnabas Poczos, and Tom Mitchell. Competence-based curriculum learning for neural machine translation. In Proc. of NAACL, 2019.","title":"Competence-based curriculum learning for neural machine translation","authors":"Otilia Emmanouil Antonios Platanios, Graham Stretcu, Barnabas Neubig, Tom Poczos, Mitchell","year":"2019","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Qin et al., 2021] Libo Qin, Minheng Ni, Yue Zhang, and Wanxiang Che. Cosda-ml: Multi-lingual code-switching data augmentation for zero-shot cross-lingual nlp. In Proc. of IJCAI, 2021.","title":"Cosda-ml: Multi-lingual code-switching data augmentation for zero-shot cross-lingual nlp","authors":"Libo Qin, Minheng Ni, Yue Zhang, Wanxiang Che","year":"2021","venue":"Proc. of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/533"},{"position":28,"raw":"[Sachan and Xing, 2016] Mrinmaya Sachan and Eric Xing. Easy questions first? a case study on curriculum learning for question answering. In Proc. of ACL, 2016.","title":"Easy questions first? a case study on curriculum learning for question answering","authors":"Xing Sachan, Mrinmaya Sachan, Eric Xing","year":"2016","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Schuster et al., 2019] Sebastian Schuster, Sonal Gupta, Rushin Shah, and Mike Lewis. Cross-lingual transfer learning for multilingual task oriented dialog. In Proc. of NAACL, 2019.","title":"Cross-lingual transfer learning for multilingual task oriented dialog","authors":"Sebastian Schuster, Sonal Gupta, Rushin Shah, Mike Lewis","year":"2019","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Schwenk and Li, 2018] Holger Schwenk and Xian Li. A corpus for multilingual document classification in eight languages. In Nicoletta Calzolari (Conference chair), Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Koiti Hasida, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis, and Takenobu Tokunaga, editors, Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Paris, France, may 2018. European Language Resources Associ- ation (ELRA).","title":"A corpus for multilingual document classification in eight languages","authors":"Li ; Schwenk, Holger Schwenk, Xian Li","year":"2018","venue":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Shen and Feng, 2020] Lei Shen and Yang Feng. CDL: Cur- riculum dual learning for emotion-controllable response generation. In Proc. of ACL, 2020.","title":"CDL: Curriculum dual learning for emotion-controllable response generation","authors":"Lei Shen, Yang Feng","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Spitkovsky et al., 2010] Valentin I. Spitkovsky, Hiyan Al- shawi, and Daniel Jurafsky. From baby steps to leapfrog: How \"less is more\" in unsupervised dependency parsing. In Proc. of NAACL, 2010.","title":"From baby steps to leapfrog: How \"less is more\" in unsupervised dependency parsing","authors":"I Valentin, Hiyan Spitkovsky, Daniel Alshawi, Jurafsky","year":"2010","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Tay et al., 2019] Yi Tay, Shuohang Wang, Anh Tuan Luu, Jie Fu, Minh C. Phan, Xingdi Yuan, Jinfeng Rao, Siu Che- ung Hui, and Aston Zhang. Simple and effective curricu- lum pointer-generator networks for reading comprehen- sion over long narratives. In Proc. of ACL, 2019.","title":"Simple and effective curriculum pointer-generator networks for reading comprehension over long narratives","authors":"Yi Tay, Shuohang Wang, Anh Tuan Luu, Jie Fu, Minh C Phan, Xingdi Yuan, Jinfeng Rao, Siu Cheung Hui, Aston Zhang","year":"2019","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Wang et al., 2023a] Fei Wang, Kuan-Hao Huang, Kai-Wei Chang, and Muhao Chen. Self-augmentation improves zero-shot cross-lingual transfer, 2023.","title":"Self-augmentation improves zero-shot cross-lingual transfer","authors":"Wang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Wang et al., 2023b] Haoyu Wang, Yaqing Wang, Feijie Wu, Hongfei Xue, and Jing Gao. Macular: A multi-task adver- sarial framework for cross-lingual natural language under- standing. In Proceedings of the 29th ACM SIGKDD Con- ference on Knowledge Discovery and Data Mining, KDD '23, page 5061-5070, New York, NY, USA, 2023. Associ- ation for Computing Machinery. Wei et al., 2021a] Jason Wei, Chengyu Huang, Soroush Vosoughi, Yu Cheng, and Shiqi Xu. Few-shot text classi- fication with triplet networks, data augmentation, and cur- riculum learning. In Proc. of NAACL, 2021.","title":"Few-shot text classification with triplet networks, data augmentation, and curriculum learning","authors":"Wang","year":"2021","venue":"Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD '23","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Wei et al., 2021b] Xiangpeng Wei, Rongxiang Weng, Yue Hu, Luxi Xing, Heng Yu, and Weihua Luo. On learn- ing universal representations across languages. In Proc. of ICLR, 2021.","title":"On learning universal representations across languages","authors":"Wei","year":"2021","venue":"Proc. of ICLR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Wu and Ong, 2021] Zhengxuan Wu and Desmond C. Ong. On explaining your explanations of bert: An empirical study with sequence classification, 2021.","title":"On explaining your explanations of bert: An empirical study with sequence classification","authors":"Ong Wu, Zhengxuan Wu, Desmond C Ong","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Xu et al., 2020] Benfeng Xu, Licheng Zhang, Zhendong Mao, Quan Wang, Hongtao Xie, and Yongdong Zhang. Curriculum learning for natural language understanding. In Proc. of ACL, 2020.","title":"Curriculum learning for natural language understanding","authors":"Xu","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Yang et al., 2019] Yinfei Yang, Yuan Zhang, Chris Tar, and Jason Baldridge. PAWS-X: A cross-lingual adversarial dataset for paraphrase identification. In Proc. of EMNLP, 2019.","title":"PAWS-X: A cross-lingual adversarial dataset for paraphrase identification","authors":"Yinfei Yang, Yuan Zhang, Chris Tar, Jason Baldridge","year":"2019","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Yang et al., 2021] Jian Yang, Yuwei Yin, Shuming Ma, Haoyang Huang, Dongdong Zhang, Zhoujun Li, and Furu Wei. Multilingual agreement for multilingual neural ma- chine translation. In Proc. of ACL, 2021.","title":"Multilingual agreement for multilingual neural machine translation","authors":"Jian Yang, Yuwei Yin, Shuming Ma, Haoyang Huang, Dongdong Zhang, Zhoujun Li, Furu Wei","year":"2021","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Zheng et al., 2021] Bo Zheng, Li Dong, Shaohan Huang, Wenhui Wang, Zewen Chi, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, and Furu Wei. Consistency reg- ularization for cross-lingual fine-tuning. In Proc. of ACL, 2021.","title":"Consistency regularization for cross-lingual fine-tuning","authors":"Bo Zheng, Li Dong, Shaohan Huang, Wenhui Wang, Zewen Chi, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei","year":"2021","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Zhu et al., 2021] Qingqing Zhu, Xiuying Chen, Pengfei Wu, JunFei Liu, and Dongyan Zhao. Combining curricu- lum learning and knowledge distillation for dialogue gen- eration. In Proc. of EMNLP Findings, 2021.","title":"Combining curriculum learning and knowledge distillation for dialogue generation","authors":"Qingqing Zhu, Xiuying Chen, Pengfei Wu, Junfei Liu, Dongyan Zhao","year":"2021","venue":"Proc. of EMNLP Findings","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}