LKMT: Linguistics Knowledge-Driven Multi-Task Neural Machine Translation for Urdu and English
Source abstract
Abstract
Thanks to the strong representation capability of pre-trained language models, supervised machine translation models have achieved outstanding performance. However, the performances of these models drop sharply when the scale... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Natural Language Processing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (62)
Show source-provided references
1. D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” Sep. 2014, arXiv:1409.0473.
2. Findings of the 2016 conference on machine translation (WMT16)
3. Findings of the 2017 conference on machine translation (WMT17)
4. Trivial transfer learning for low-resource neural machine translation
5. Y. Wu et al., “Google’s neural machine translation system: Bridging the gap between human and machine translation,” Sep. 2016, arXiv:1609.08144.
6. H. Hassan et al., “Achieving human parity on automatic chinese to english news translation,” Mar. 2018, arXiv:1803.05567.
7. Multi-task learning for multiple language translation
8. Zero-resource translation with multi-lingual neural machine translation
9. T. -L. Ha, J. Niehues, and A. Waibel, “Toward multilingual neural machine translation with universal encoder and decoder,” Nov. 2016, arXiv:1611.04798.
10. Google’s multilingual neural machine translation system: enabling zero-shot translation10.1162/tacl_a_00065 ↗
11. K. Cho, B. van Merrienboer, D. Bahdanau, and Y. Bengio, “On the properties of neural machine translation: encoder-decoder approaches,” Sep. 2014, arXiv:1409.1259.10.3115/v1/W14-4012 ↗
12. A. Vaswani et al., “Attention is all you need,” Jun. 2017, arXiv:1706.03762.
13. Cutting-off redundant repeating generations for neural abstractive summarization
14. Convolutional sequence to sequence learning, Convolutional sequence to sequence learning
15. Grammar as a foreign language
16. J. Devlin, M. -W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” 2019, arXiv:1810.04805.
17. Y. Liu et al., “RoBERTa: A robustly optimized BERT pretraining approach,” Jul. 2019, arXiv:1907.11692.
18. A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever, “Improving language understanding by generative pre-training,” 2018. Accessed: May 10, 2024. [Online]. Available: https://www.cs.ubc.ca/~amuham01/LING530/papers/radford2018improving.pdf.
19. Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma and R. Soricut, “ALBERT: A lite BERT for self-supervised learning of language representations,” Sep. 2019, arXiv:1909.11942.
20. Z. Zhang, X. Han, Z. Liu, X. Jiang, M. Sun and Q. Liu, “ERNIE: enhanced language representation with informative entities,” May 2019, arXiv:1905.07129.10.18653/v1/P19-1139 ↗
21. P. He, X. Liu, J. Gao, and W. Chen, “DeBERTa: Decoding-enhanced BERT with disentangled attention,” Jun. 2020, arXiv:2006.03654.
22. Linguistically driven multi-task pre-training for low-resource neural machine translation10.1145/3491065 ↗
23. T. Mikolov, I. Sutskever, K. Chen, G. Corrado, and J. Dean, “Distributed representations of words and phrases and their compositionality,” Oct. 2013, arXiv:1310.4546.
24. GloVe: Global vectors for word representation
25. Deep fusing pre-trained models into neural machine translation
26. L. Han, G. Erofeev, I. Sorokina, S. Gladkoff, and G. Nenadic, “Examining large pre-trained language models for machine translation: What you don’t know about it,” 2022, arXiv:2209.07417.
27. Z. Sun, M. Wang, and L. Li, “Multilingual translation via grafting pre-trained language models,” 2021, arXiv:2109.05256.10.18653/v1/2021.findings-emnlp.233 ↗
28. Universal conditional masked language pre-training for neural machine translation
29. J. Hwang and C. -S. Jeong, “Integrating pre-trained language model into neural machine translation,” Oct. 2023, arXiv:2310.19680.10.1109/CISDS61173.2023.00019 ↗
30. Multilingual denoising pre-training for neural machine translation10.1162/tacl_a_00343 ↗
31. Reinforced curriculum learning on pre-trained neural machine translation models
32. Z. He, G. Blackwood, R. Panda, J. McAuley, and R. Feris, “Synthetic pre-training tasks for neural machine translation,” 2022, arXiv:2212.09864.10.18653/v1/2023.findings-acl.512 ↗
33. Acquiring knowledge from pre-trained model to neural machine translation
34. Machine translation system using deep learning for english to Urdu10.1155/2022/7873012 ↗
35. H. S. Shavarani and A. Sarkar, “Better neural machine translation by extracting linguistic information from BERT,” 2021, arXiv:2104.02831.10.18653/v1/2021.eacl-main.241 ↗
36. Linguistic knowledge-aware neural machine translation10.1109/TASLP.2018.2864648 ↗
37. Linguistically enhanced word segmentation for better neural machine translation of low resource agglutinative languages10.1007/s10772-021-09865-5 ↗
38. Experience of neural machine translation between Indian languages10.1007/s10590-021-09263-3 ↗
39. Multi-source neural model for machine translation of agglutinative language10.3390/fi12060096 ↗
40. Unsupervised neural machine translation for english to kannada using pre-trained language model
41. Low-resource multilingual neural translation using linguistic feature-based relevance mechanisms10.1145/3594631 ↗
42. H. Choudhary, S. Rao, and R. Rohilla, “Neural machine translation for low-resourced Indian languages,” 2020, arXiv:2004.13819.
43. P. Zaremoodi and G. Haffari, “Learning to multi-task learn for better neural machine translation,” Jan. 2020, arXiv:2001.03294.
44. Improving neural machine translation with latent features feedback10.1016/j.neucom.2021.08.019 ↗
45. Robust domain adaptation for pre-trained multilingual neural machine translation models
46. X. Liu et al., “On the copying behaviors of pre-training for neural machine translation,” 2021, arXiv:2107.08212.10.18653/v1/2021.findings-acl.373 ↗
47. Factors behind the effectiveness of an unsupervised neural machine translation system between Korean and Japanese
48. Towards making the most of BERT in neural machine translation
49. P. Qi, Y. Zhang, Y. Zhang, J. Bolton, and C. D. Manning, “Stanza: A python natural language processing toolkit for many human languages,” Mar. 2020, arXiv:2003.07082.10.18653/v1/2020.acl-demos.14 ↗
50. A tagged corpus and a tagger for Urdu
51. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” Dec. 2014, arXiv:1412.6980.
52. G. Lample, M. Ott, A. Conneau, L. Denoyer, and M. Ranzato, “Phrase-based & neural unsupervised machine translation,” Apr. 2018, arXiv:1804.07755.10.18653/v1/D18-1549 ↗
53. Cross-lingual language model pretraining
54. K. Song, X. Tan, T. Qin, J. Lu, and T. -Y. Liu, “MASS: Masked sequence to sequence pre-training for language generation,” May 2019, arXiv:1905.02450.
55. Pre-training multilingual neural machine translation by leveraging alignment information
56. IndicBART: A pre-trained model for indic natural language generation
57. H. Qin et al., “BIBERT: Accurate fully binarized BERT,” 2022, arXiv:2203.06390.
58. M. R. Costa-jussà et al., “No language left behind: Scaling human-centered machine translation,” 2022, arXiv:2207.04672.
59. The Flores-101 evaluation benchmark for low-resource and multilingual machine translation10.1162/tacl_a_00474 ↗
60. Parallel data, tools and interfaces in OPUS
61. Word-order issues in english-to-urdu statistical machine translation10.2478/v10108-011-0007-0 ↗
62. An improved neural network model for joint POS tagging and dependency parsing