English
Related papers

Related papers: Sparse Sequence-to-Sequence Models

200 papers

Neural network models are widely used in solving many challenging problems, such as computer vision, personalized recommendation, and natural language processing. Those models are very computationally intensive and reach the hardware limit…

Machine Learning · Computer Science 2020-04-28 Fei Sun , Minghai Qin , Tianyun Zhang , Liu Liu , Yen-Kuang Chen , Yuan Xie

In this work, we conduct a systematic analysis of Native Sparse Attention (NSA) and propose targeted improvements that enhance long-context modeling. A key insight is that alternating between local (sliding-window) and global (compression,…

Computation and Language · Computer Science 2025-11-04 Yuxuan Hu , Jianchao Tan , Jiaqi Zhang , Wen Zan , Pingwei Sun , Yifan Lu , Yerui Sun , Yuchen Xie , Xunliang Cai , Jing Zhang

Accelerating large language model (LLM) inference is critical for real-world deployments requiring high throughput and low latency. Contextual sparsity, where each token dynamically activates only a small subset of the model parameters,…

Machine Learning · Computer Science 2025-11-13 Susav Shrestha , Brad Settlemyer , Nikoli Dryden , Narasimha Reddy

This paper investigates whether sequence models can learn to perform numerical algorithms, e.g. gradient descent, on the fundamental problem of least squares. Our goal is to inherit two properties of standard algorithms from numerical…

Machine Learning · Computer Science 2025-03-18 Jerry Liu , Jessica Grogan , Owen Dugan , Ashish Rao , Simran Arora , Atri Rudra , Christopher Ré

The input to a neural sequence-to-sequence model is often determined by an up-stream system, e.g. a word segmenter, part of speech tagger, or speech recognizer. These up-stream models are potentially error-prone. Representing inputs through…

Computation and Language · Computer Science 2017-07-24 Matthias Sperber , Graham Neubig , Jan Niehues , Alex Waibel

Feature selection is a critical component in predictive analytics that significantly affects the prediction accuracy and interpretability of models. Intrinsic methods for feature selection are built directly into model learning, providing a…

Machine Learning · Computer Science 2024-03-19 Theodor Stoecker , Nico Hambauer , Patrick Zschech , Mathias Kraus

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks. The attention mechanism in the Transformer…

Computation and Language · Computer Science 2023-04-27 Shuai Li , Zhao Song , Yu Xia , Tong Yu , Tianyi Zhou

The softmax representation of probabilities for categorical variables plays a prominent role in modern machine learning with numerous applications in areas such as large scale classification, neural language modeling and recommendation…

Machine Learning · Statistics 2016-11-01 Michalis K. Titsias

For reliability, it is important that the predictions made by machine learning methods are interpretable by human. In general, deep neural networks (DNNs) can provide accurate predictions, although it is difficult to interpret why such…

Machine Learning · Computer Science 2021-12-16 Yuya Yoshikawa , Tomoharu Iwata

Large language models (LLMs) have brought significant and transformative changes in human society. These models have demonstrated remarkable capabilities in natural language understanding and generation, leading to various advancements and…

Machine Learning · Computer Science 2023-07-06 Yeqi Gao , Zhao Song , Shenghao Xie

Deep Neural Networks (DNNs) have performed admirably in classification tasks. However, the characterization of their classification uncertainties, required for certain applications, has been lacking. In this work, we investigate the issue…

Machine Learning · Computer Science 2023-11-28 Yu Pan , Kwo-Sen Kuo , Michael L. Rilee , Hongfeng Yu

Copy mechanisms are employed in sequence to sequence models (seq2seq) to generate reproductions of words from the input to the output. These frameworks, operating at the lexical type level, fail to provide an explicit alignment that records…

Computation and Language · Computer Science 2020-10-30 Abhinav Singh , Patrick Xia , Guanghui Qin , Mahsa Yarmohammadi , Benjamin Van Durme

The use of contrastive loss for representation learning has become prominent in computer vision, and it is now getting attention in Natural Language Processing (NLP). Here, we explore the idea of using a batch-softmax contrastive loss when…

Computation and Language · Computer Science 2021-11-01 Anton Chernyavskiy , Dmitry Ilvovsky , Pavel Kalinin , Preslav Nakov

In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via…

Computation and Language · Computer Science 2017-07-31 Allen Schmaltz , Yoon Kim , Alexander M. Rush , Stuart M. Shieber

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, we introduce a novel, simple method for achieving sparsity in…

Computation and Language · Computer Science 2021-10-07 Biao Zhang , Ivan Titov , Rico Sennrich

Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning…

Computation and Language · Computer Science 2019-06-12 Hui Liu , Qingyu Yin , William Yang Wang

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge

Linear recurrent neural networks (RNNs) and state-space models (SSMs) such as Mamba have become promising alternatives to softmax-attention as sequence mixing layers in Transformer architectures. Current models, however, do not exhibit the…

Machine Learning · Computer Science 2025-10-27 Sajad Movahedi , Felix Sarnthein , Nicola Muca Cirone , Antonio Orvieto

In a typical fusion experiment, the plasma can have several possible confinement modes. At the TCV tokamak, aside from the Low (L) and High (H) confinement modes, an additional mode, dithering (D), is frequently observed. Developing methods…

Plasma Physics · Physics 2021-05-26 Francisco Matos , Vlado Menkovski , Alessandro Pau , Gino Marceca , Frank Jenko

While fine-tuning pre-trained models for downstream classification is the conventional paradigm in NLP, often task-specific nuances may not get captured in the resultant models. Specifically, for tasks that take two inputs and require the…

Computation and Language · Computer Science 2022-03-28 Ashutosh Kumar , Aditya Joshi
‹ Prev 1 4 5 6 7 8 10 Next ›