English
Related papers

Related papers: Does Transformer Interpretability Transfer to RNNs…

200 papers

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

Computation and Language · Computer Science 2018-09-06 Ankur Bapna , Mia Xu Chen , Orhan Firat , Yuan Cao , Yonghui Wu

Neural network models have achieved state-of-the-art performances in a wide range of natural language processing (NLP) tasks. However, a long-standing criticism against neural network models is the lack of interpretability, which not only…

Computation and Language · Computer Science 2021-10-26 Xiaofei Sun , Diyi Yang , Xiaoya Li , Tianwei Zhang , Yuxian Meng , Han Qiu , Guoyin Wang , Eduard Hovy , Jiwei Li

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Computation and Language · Computer Science 2021-08-06 Wenjuan Han , Bo Pang , Yingnian Wu

We propose Factorization Memory, an efficient recurrent neural network (RNN) architecture that achieves performance comparable to Transformer models on short-context language modeling tasks while also demonstrating superior generalization…

Computation and Language · Computer Science 2025-11-04 Lee Xiong , Maksim Tkachenko , Johanes Effendi , Ting Cai

Transformers have become increasingly popular for image super-resolution (SR) tasks due to their strong global context modeling capabilities. However, their quadratic computational complexity necessitates the use of window-based attention…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Aman Urumbekov , Zheng Chen

We introduce the concept of multiple temporal perspectives, a novel approach applicable to Recurrent Neural Network (RNN) architectures for enhancing their understanding of sequential data. This method involves maintaining diverse temporal…

Machine Learning · Computer Science 2024-07-15 Razvan-Gabriel Dumitru , Darius Peteleaza , Mihai Surdeanu

Recently, fully recurrent neural network (RNN) based end-to-end models have been proven to be effective for multi-speaker speech recognition in both the single-channel and multi-channel scenarios. In this work, we explore the use of…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-14 Xuankai Chang , Wangyou Zhang , Yanmin Qian , Jonathan Le Roux , Shinji Watanabe

Recently, strong results have been demonstrated by Deep Recurrent Neural Networks on natural language transduction problems. In this paper we explore the representational power of these models using synthetic grammars designed to exhibit…

Neural and Evolutionary Computing · Computer Science 2015-11-04 Edward Grefenstette , Karl Moritz Hermann , Mustafa Suleyman , Phil Blunsom

Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a significant computational cost, as the attention mechanism's complexity scales quadratically with sequence length.…

Computation and Language · Computer Science 2021-09-21 Jungo Kasai , Hao Peng , Yizhe Zhang , Dani Yogatama , Gabriel Ilharco , Nikolaos Pappas , Yi Mao , Weizhu Chen , Noah A. Smith

Vision language tasks, such as answering questions about or generating captions that describe an image, are difficult tasks for computers to perform. A relatively recent body of research has adapted the pretrained transformer architecture…

Computer Vision and Pattern Recognition · Computer Science 2023-07-10 Clayton Fields , Casey Kennington

Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inference-time memory requirements from the key-value cache.…

Transformer-based models have transformed the landscape of natural language processing (NLP) and are increasingly applied to computer vision tasks with remarkable success. These models, renowned for their ability to capture long-range…

Computer Vision and Pattern Recognition · Computer Science 2024-08-28 Gracile Astlin Pereira , Muhammad Hussain

For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of…

Machine Learning · Computer Science 2019-05-30 Tian Guo , Tao Lin , Nino Antulov-Fantulin

Transformer architectures have become a dominant paradigm for domains like language modeling but suffer in many inference settings due to their quadratic-time self-attention. Recently proposed subquadratic architectures, such as Mamba, have…

Machine Learning · Computer Science 2025-02-11 Aviv Bick , Kevin Y. Li , Eric P. Xing , J. Zico Kolter , Albert Gu

Recursive neural networks (RvNN) have been shown useful for learning sentence representations and helped achieve competitive performance on several natural language inference tasks. However, recent RvNN-based models fail to learn simple…

Computation and Language · Computer Science 2021-04-13 Atul Sahay , Ayush Maheshwari , Ritesh Kumar , Ganesh Ramakrishnan , Manjesh Kumar Hanawal , Kavi Arya

Even though sequence-to-sequence neural machine translation (NMT) model have achieved state-of-art performance in the recent fewer years, but it is widely concerned that the recurrent neural network (RNN) units are very hard to capture the…

Computation and Language · Computer Science 2018-05-28 Wen Zhang , Jiawei Hu , Yang Feng , Qun Liu

In modern machine (ML) learning systems, Transformer-based architectures have achieved milestone success across a broad spectrum of tasks, yet understanding their operational mechanisms remains an open problem. To improve the transparency…

Machine Learning · Computer Science 2024-06-11 Yihao Zhang , Zeming Wei , Meng Sun

Although self-attention based models such as Transformers have achieved remarkable successes on natural language processing (NLP) tasks, recent studies reveal that they have limitations on modeling sequential transformations (Hahn, 2020),…

Computation and Language · Computer Science 2022-05-06 Xiaobing Sun , Wei Lu

Recurrent Neural Networks (RNNs) are theoretically Turing-complete and established themselves as a dominant model for language processing. Yet, there still remains an uncertainty regarding their language learning capabilities. In this…

Computation and Language · Computer Science 2018-11-05 Mirac Suzgun , Yonatan Belinkov , Stuart M. Shieber

Reasoning-oriented large language models (RLMs) achieve strong gains on tasks such as mathematics and coding by generating explicit intermediate reasoning. However, their impact on machine translation (MT) remains underexplored. We…

Computation and Language · Computer Science 2026-02-17 Sara Rajaee , Sebastian Vincent , Alexandre Berard , Marzieh Fadaee , Kelly Marchisio , Tom Kocmi