English
Related papers

Related papers: Look Backward and Forward: Self-Knowledge Distilla…

200 papers

We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed…

Computation and Language · Computer Science 2019-04-05 Xing Niu , Weijia Xu , Marine Carpuat

Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks. However, existing knowledge distillation has side effects, such as propagating…

Computation and Language · Computer Science 2023-08-07 Min Liu , Yu Bao , Chengqi Zhao , Shujian Huang

Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the…

Computation and Language · Computer Science 2021-10-18 Fahimeh Saleh , Wray Buntine , Gholamreza Haffari , Lan Du

Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a…

Computation and Language · Computer Science 2017-08-09 Markus Freitag , Yaser Al-Onaizan , Baskaran Sankaran

Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high…

Computation and Language · Computer Science 2019-08-07 Sangchul Hahn , Heeyoul Choi

Neural Machine Translation (NMT) has become a popular technology in recent years, and the encoder-decoder framework is the mainstream among all the methods. It's obvious that the quality of the semantic representations from encoding is very…

Computation and Language · Computer Science 2020-01-15 Boyuan Pan , Yazheng Yang , Zhou Zhao , Yueting Zhuang , Deng Cai

Non-autoregressive neural machine translation (NAT) usually employs sequence-level knowledge distillation using autoregressive neural machine translation (AT) as its teacher model. However, a NAT model often outputs shorter sentences than…

Computation and Language · Computer Science 2021-07-30 Yui Oka , Katsuhito Sudoh , Satoshi Nakamura

Neural machine translation (NMT) has recently become popular in the field of machine translation. However, NMT suffers from the problem of repeating or missing words in the translation. To address this problem, Tu et al. (2017) proposed an…

Computation and Language · Computer Science 2017-06-27 Yukio Matsumura , Takayuki Sato , Mamoru Komachi

Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the…

Machine Learning · Computer Science 2021-03-26 Zhenyan Hou , Wenxuan Fan

We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We convert decoding - basically a discrete optimization problem - into a continuous optimization problem. The resulting constrained…

Computation and Language · Computer Science 2017-07-25 Cong Duy Vu Hoang , Gholamreza Haffari , Trevor Cohn

Improving neural machine translation (NMT) models using the back-translations of the monolingual target data (synthetic parallel data) is currently the state-of-the-art approach for training improved translation systems. The quality of the…

Computation and Language · Computer Science 2021-02-16 Idris Abdulmumin , Bashir Shehu Galadanci , Abubakar Isa

Recommender systems (RS) have started to employ knowledge distillation, which is a model compression technique training a compact model (student) with the knowledge transferred from a cumbersome model (teacher). The state-of-the-art methods…

Information Retrieval · Computer Science 2021-06-08 Wonbin Kweon , SeongKu Kang , Hwanjo Yu

Although teacher forcing has become the main training paradigm for neural machine translation, it usually makes predictions only conditioned on past information, and hence lacks global planning for the future. To address this problem, we…

Computation and Language · Computer Science 2021-06-15 Yang Feng , Shuhao Gu , Dengji Guo , Zhengxin Yang , Chenze Shao

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

Computation and Language · Computer Science 2020-10-13 Fahimeh Saleh , Wray Buntine , Gholamreza Haffari

Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…

Machine Learning · Computer Science 2023-01-31 Aref Jafari , Mehdi Rezagholizadeh , Ali Ghodsi

The performance of deep neural networks is well-known to be sensitive to the setting of their hyperparameters. Recent advances in reverse-mode automatic differentiation allow for optimizing hyperparameters with gradients. The standard way…

Machine Learning · Computer Science 2016-04-07 Jie Fu , Hongyin Luo , Jiashi Feng , Kian Hsiang Low , Tat-Seng Chua

Pre-training and fine-tuning have achieved great success in the natural language process field. The standard paradigm of exploiting them includes two steps: first, pre-training a model, e.g. BERT, with a large scale unlabeled monolingual…

Computation and Language · Computer Science 2019-12-05 Rongxiang Weng , Heng Yu , Shujian Huang , Shanbo Cheng , Weihua Luo

Previous studies have shown that neural machine translation (NMT) models can benefit from explicitly modeling translated (Past) and untranslated (Future) to groups of translated and untranslated contents through parts-to-wholes assignment.…

Computation and Language · Computer Science 2019-09-23 Zaixiang Zheng , Shujian Huang , Zhaopeng Tu , Xin-Yu Dai , Jiajun Chen

Deep neural network architectures have attained remarkable improvements in scene understanding tasks. Utilizing an efficient model is one of the most important constraints for limited-resource devices. Recently, several compression methods…

Computer Vision and Pattern Recognition · Computer Science 2020-10-12 Mahdi Ghorbani , Fahimeh Fooladgar , Shohreh Kasaei

Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel…

Computation and Language · Computer Science 2024-07-18 Songming Zhang , Yunlong Liang , Shuaibo Wang , Wenjuan Han , Jian Liu , Jinan Xu , Yufeng Chen