\parinterval 此外,还有很多工作对如何将语言模型应用到神经机器翻译模型中进行了研究。研究人员分析了预训练词嵌入何时为何在神经机器翻译模型中有效[When and Why are Pre-trained Word Embeddings Useful for NMT];如何在神经机器翻译模型中利用预训练的BERT模型[On the use of BERT for Neural Machine Translation][Recycling a Pre-trained BERT Encoder for Neural Machine Translation][Towards Making the Most of BERT in Neural Machine Translation][Acquiring Knowledge from Pre-trained Model to Neural Machine Translation];如何针对神经机器翻译任务进行预训练[Multilingual Denoising Pre-training for Neural Machine Translation][Cross-Lingual Pre-Training Based Transfer for Zero-Shot Neural Machine Translation][ BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension];针对机器翻译中的Code-switching问题进行预训练[Code-switching pre-training for neural machine translation];如何在微调过程中避免遗忘原始的语言模型任务[Unsupervised Pretraining for Neural Machine Translation Using Elastic Weight Consolidation]。
[1] Alan R, Barbara P. Neural Unsupervised Domain Adaptation in NLP---A Survey[J]. 2020.
[2] Ievgen R, Emilie M, Amaury H, et al. A survey on domain adaptation theory[J]. 2020.
[1] Chu, Chenhui, and Rui Wang. "A Survey of Domain Adaptation for Neural Machine Translation.." abs/1806.00258 (2018): 1304-1319.
[2] Chu C, Dabre R, Kurohashi S. An Empirical Com-parison of Domain Adaptation Methods for Neural Machine Translation[J]. ACL. 2017: 385-391.
[3] Axelrod A, He X, Gao J. Domain Adaptation via Pseudo In-Domain Data Selection[Z]. Edinburgh(GB): 2011355-362.
[4] Remus R. Domain Adaptation Using Domain Similarity- and Domain Complexity-Based Instance Selection for Cross-Domain Sentiment Analysis[J]. ICDM Workshops. 2012: 717-723.
[5] Wang R, Finch M A, Utiyama M, et al. Sentence Embedding for Neural Machine Translation Domain Adaptation[J]. ACL. 2017: 560-566.
...
...
@@ -567,17 +645,15 @@ g_{t} = \sigma (w^{T}s_{t}^{TM} + b)
[13] Kim Y, Gao Y, Ney H. Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies[J]. Meeting of the Association for Computational Linguistics. 2019.
[14] Hu J, Xia M, Neubig G, et al. Domain Adaptation of Neural Machine Translation by Lexicon Induction[J]. ACL (1). 2019: 2989-3001.
[15] Wang R, Utiyama M, Liu L, et al. Instance Weighting for Neural Machine Translation Domain Adaptation[J]. EMNLP. 2017: 1483-1489.
[16] Chen B, Cherry C, Foster F G, et al. Cost Weighting for Neural Machine Translation Domain Adaptation[J]. NMT@ACL. 2017: 40-46.
[17] Yan S, Dahlmann L, Petrushkov P, et al. Word-based Domain Adaptation for Neural Machine Translation[J]. CoRR. 2019.
[18] Dakwale P, Monz C. Fine-Tuning for Neural Machine Translation with Limited Degradation across In- and Out-of-Domain Data[Z]. 2017156-169.
[19] Chu C. Integrated Parallel Data Extraction from Comparable Corpora for Statistical Machine Translation[J]. 2015.
[20] Zeng J, Liu Y, Su J, et al. Iterative Dual Domain Adaptation for Neural Machine Translation[J]. EMNLP/IJCNLP (1). 2019: 845-855.
[21] Barone V M A, Haddow B, Germann U, et al. Regularization techniques for fine-tuning in neural machine translation[J]. EMNLP. 2017: 1489-1494.
[22] Gulcehre C, Firat O, Xu K, et al. On Using Monolingual Corpora in Neural Machine Translation[J]. Computer Science. 2015.
[23] Britz D, Le V Q, Pryzant R. Effective Domain Mixing for Neural Machine Translation[J]. WMT. 2017: 118-126.
[24] Kobus C, Crego M J, Senellart J. Domain Control for Neural Machine Translation[J]. recent advances in natural language processing. 2017.
[25] Dou Z, Wang X, Hu J, et al. Domain Differential Adaptation for Neural Machine Translation[J]. NGT@EMNLP-IJCNLP. 2019: 59-69.
[26] Freitag M, Al-Onaizan Y. Fast Domain Adaptation for Neural Machine Translation[J]. 2016.
[27] Saunders D, Stahlberg F, Gispert D A A, et al. Domain Adaptive Inference for Neural Machine Translation[J]. Meeting of the Association for Computational Linguistics. 2019.
[28] Khayrallah H, Kumar G, Duh K, et al. Neural Lattice Search for Domain Adaptation in Machine Translation[J]. IJCNLP. 2017: 20-25.
[16] Yan S, Dahlmann L, Petrushkov P, et al. Word-based Domain Adaptation for Neural Machine Translation[J]. CoRR. 2019.
[17] Zeng J, Liu Y, Su J, et al. Iterative Dual Domain Adaptation for Neural Machine Translation[J]. EMNLP/IJCNLP (1). 2019: 845-855.
[18] Britz D, Le V Q, Pryzant R. Effective Domain Mixing for Neural Machine Translation[J]. WMT. 2017: 118-126.
[19] Kobus C, Crego M J, Senellart J. Domain Control for Neural Machine Translation[J]. recent advances in natural language processing. 2017.
[20] Khayrallah H, Kumar G, Duh K, et al. Neural Lattice Search for Domain Adaptation in Machine Translation[J]. IJCNLP. 2017: 20-25.
[21] Gulcehre C, Firat O, Xu K, et al. On Using Monolingual Corpora in Neural Machine Translation[J]. Computer Science. 2015.
[22] Dou Z, Wang X, Hu J, et al. Domain Differential Adaptation for Neural Machine Translation[J]. NGT@EMNLP-IJCNLP. 2019: 59-69.
[23] Freitag M, Al-Onaizan Y. Fast Domain Adaptation for Neural Machine Translation[J]. 2016.
[24] Saunders D, Stahlberg F, Gispert D A A, et al. Domain Adaptive Inference for Neural Machine Translation[J]. Meeting of the Association for Computational Linguistics. 2019.