English
Related papers

Related papers: Critical Learning Periods: Leveraging Early Traini…

200 papers

Vision-language foundation models have been incredibly successful in a wide range of downstream computer vision tasks using adaptation methods. However, due to the high cost of obtaining pre-training datasets, pairs with weak image-text…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Wenshuo Peng , Kaipeng Zhang , Yue Yang , Hao Zhang , Yu Qiao

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

Computation and Language · Computer Science 2022-01-19 Dongkuan Xu , Ian E. H. Yen , Jinxi Zhao , Zhibin Xiao

Neural Machine Translation (NMT) models are typically trained on heterogeneous data that are concatenated and randomly shuffled. However, not all of the training data are equally useful to the model. Curriculum training aims to present the…

Computation and Language · Computer Science 2022-03-29 Tasnim Mohiuddin , Philipp Koehn , Vishrav Chaudhary , James Cross , Shruti Bhosale , Shafiq Joty

The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's…

Machine Learning · Computer Science 2023-02-28 Shuo Yang , Zeke Xie , Hanyu Peng , Min Xu , Mingming Sun , Ping Li

Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models. In this work, we propose a novel model adaptation paradigm, adapting by pruning, which prunes neural connections in…

Machine Learning · Computer Science 2021-05-10 Yang Gao , Nicolo Colombo , Wei Wang

Checkpoint averaging is a simple and effective method to boost the performance of converged neural machine translation models. The calculation is cheap to perform and the fact that the translation improvement almost comes for free, makes it…

Computation and Language · Computer Science 2022-10-24 Yingbo Gao , Christian Herold , Zijian Yang , Hermann Ney

As large language models (LLMs) are widely applied across various fields, model compression has become increasingly crucial for reducing costs and improving inference efficiency. Post-training pruning is a promising method that does not…

Computation and Language · Computer Science 2025-07-01 Yixin Ji , Yang Xiang , Juntao Li , Qingrong Xia , Ping Li , Xinyu Duan , Zhefeng Wang , Min Zhang

Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a…

Computation and Language · Computer Science 2019-10-09 Alberto Poncelas , Gideon Maillette de Buy Wenniger , Andy Way

To mitigate the negative effect of low quality training data on the performance of neural machine translation models, most existing strategies focus on filtering out harmful data before training starts. In this paper, we explore strategies…

Computation and Language · Computer Science 2021-03-01 Xinyi Wang , Ankur Bapna , Melvin Johnson , Orhan Firat

Non-autoregressive translation (NAT) models remove the dependence on previous target tokens and generate all target tokens in parallel, resulting in significant inference speedup but at the cost of inferior translation accuracy compared to…

Machine Learning · Computer Science 2019-11-25 Junliang Guo , Xu Tan , Linli Xu , Tao Qin , Enhong Chen , Tie-Yan Liu

Pre-trained universal feature extractors, such as BERT for natural language processing and VGG for computer vision, have become effective methods for improving deep learning models without requiring more labeled data. While effective,…

Computation and Language · Computer Science 2020-05-18 Mitchell A. Gordon , Kevin Duh , Nicholas Andrews

The quadratic cost of attention in transformers motivated the development of efficient approaches: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in…

Machine Learning · Computer Science 2025-11-10 Jatin Prakash , Aahlad Puli , Rajesh Ranganath

System identification is normally involved in augmenting time series data by time shifting and nonlinearisation (e.g., polynomial basis), both of which introduce redundancy in features and samples. Many research works focus on reducing…

Machine Learning · Computer Science 2025-09-05 Tingna Wang , Sikai Zhang , Mingming Song , Limin Sun

Multilingual machine translation models often outperform traditional bilingual models by leveraging translation knowledge transfer. Recent advancements have led to these models supporting hundreds of languages and achieving state-of-the-art…

Computation and Language · Computer Science 2024-11-12 Pedram Rostami , Mohammad Javad Dousti

There is an increase in the proliferation of online hate commensurate with the rise in the usage of social media. In response, there is also a significant advancement in the creation of automated tools aimed at identifying harmful text…

Computation and Language · Computer Science 2024-06-10 Rabiraj Bandyopadhyay , Dennis Assenmacher , Jose M. Alonso Moral , Claudia Wagner

Language Model (LM) pruning compresses the model by removing weights, nodes, or other parts of its architecture. Typically, pruning focuses on the resulting efficiency gains at the cost of effectiveness. However, when looking at how…

Computation and Language · Computer Science 2025-03-28 Pietro Tropeano , Maria Maistro , Tuukka Ruotsalo , Christina Lioma

Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where…

Computation and Language · Computer Science 2021-03-23 Chen Liang , Haoming Jiang , Xiaodong Liu , Pengcheng He , Weizhu Chen , Jianfeng Gao , Tuo Zhao

Classical translation models constrain the space of possible outputs by selecting a subset of translation rules based on the input sentence. Recent work on improving the efficiency of neural translation models adopted a similar strategy by…

Computation and Language · Computer Science 2016-10-04 Gurvan L'Hostis , David Grangier , Michael Auli

Quantization and pruning are fundamental approaches for model compression, enabling efficient inference for language models. In a post-training setting, state-of-the-art quantization and pruning methods require calibration data, a small set…

Computation and Language · Computer Science 2025-07-15 Miles Williams , George Chrysostomou , Nikolaos Aletras

Large language models (LLMs) have revolutionized natural language processing, yet their substantial model sizes often require substantial computational resources. To preserve computing resources and accelerate inference speed, it is crucial…

Computation and Language · Computer Science 2025-06-04 Yirao Zhao , Guizhen Chen , Kenji Kawaguchi , Lidong Bing , Wenxuan Zhang