English
Related papers

Related papers: Breaking the Activation Function Bottleneck throug…

200 papers

Many advances in Natural Language Processing have been based upon more expressive models for how inputs interact with the context in which they occur. Recurrent networks, which have enjoyed a modicum of success, still lack the…

Computation and Language · Computer Science 2020-01-30 Gábor Melis , Tomáš Kočiský , Phil Blunsom

Transformer-based language models have recently been at the forefront of active research in text generation. However, these models' advances come at the price of prohibitive training costs, with parameter counts in the billions and compute…

Computation and Language · Computer Science 2025-02-04 Gabriel Lindenmaier , Sean Papay , Sebastian Padó

Despite the increasing prevalence of deep neural networks, their applicability in resource-constrained devices is limited due to their computational load. While modern devices exhibit a high level of parallelism, real-time latency is still…

Computer Vision and Pattern Recognition · Computer Science 2021-09-06 Amir Ben Dror , Niv Zehngut , Avraham Raviv , Evgeny Artyomov , Ran Vitek , Roy Jevnisek

We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with a multi-layer perceptron, our base system…

Computation and Language · Computer Science 2017-04-27 Hao Peng , Sam Thomson , Noah A. Smith

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the…

Machine Learning · Computer Science 2019-10-01 Farnoush Farhadi , Vahid Partovi Nia , Andrea Lodi

The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks. To address this issue, parameter-efficient transfer learning methods have been proposed to…

Computation and Language · Computer Science 2022-10-27 Yifan Chen , Devamanyu Hazarika , Mahdi Namazifar , Yang Liu , Di Jin , Dilek Hakkani-Tur

Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing methods mitigate catastrophic forgetting by data replay,…

Machine Learning · Computer Science 2026-05-08 Yazheng Liu , Yuxuan Wan , Rui Xu , Xi Zhang , Sihong Xie , Hui Xiong

We formulate language modeling as a matrix factorization problem, and show that the expressiveness of Softmax-based models (including the majority of neural language models) is limited by a Softmax bottleneck. Given that natural language is…

Computation and Language · Computer Science 2018-03-06 Zhilin Yang , Zihang Dai , Ruslan Salakhutdinov , William W. Cohen

The transformer is a state-of-the-art neural translation model that uses attention to iteratively refine lexical representations with information drawn from the surrounding context. Lexical features are fed into the first layer and…

Computation and Language · Computer Science 2019-07-01 Denis Emelin , Ivan Titov , Rico Sennrich

Foundational vision transformer models have shown impressive few shot performance on many vision tasks. This research presents a novel investigation into the application of parameter efficient fine-tuning methods within an active learning…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Athmanarayanan Lakshmi Narayanan , Ranganath Krishnan , Amrutha Machireddy , Mahesh Subedar

We explore whether it is possible to build lighter parsers, that are statistically equivalent to their corresponding standard version, for a wide set of languages showing different structures and morphologies. As testbed, we use the…

Computation and Language · Computer Science 2018-10-23 David Vilares , Carlos Gómez-Rodríguez

Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against…

Machine Learning · Computer Science 2017-03-14 Hakan Inan , Khashayar Khosravi , Richard Socher

Random feature (RF) method is a powerful kernel approximation technique, but is typically equipped with fixed activation functions, limiting its adaptability across diverse tasks. To overcome this limitation, we introduce the Random Feature…

Machine Learning · Computer Science 2025-11-06 Zailin Ma , Jiansheng Yang , Yaodong Yang

The current paradigm of large-scale pre-training and fine-tuning Transformer large language models has lead to significant improvements across the board in natural language processing. However, such large models are susceptible to…

Machine Learning · Computer Science 2023-12-04 Fabio Fehr , James Henderson

This study explores novel activation functions that enhance the ability of neural networks to manipulate data topology during training. Building on the limitations of traditional activation functions like $\mathrm{ReLU}$, we propose…

Machine Learning · Computer Science 2025-07-18 Pavel Snopov , Oleg R. Musin

Natural language is hierarchically structured: smaller units (e.g., phrases) are nested within larger units (e.g., clauses). When a larger constituent ends, all of the smaller constituents that are nested within it must also be closed.…

Computation and Language · Computer Science 2019-05-09 Yikang Shen , Shawn Tan , Alessandro Sordoni , Aaron Courville

The layered structure of deep neural networks hinders the use of numerous analysis tools and thus the development of its interpretability. Inspired by the success of functional brain networks, we propose a novel framework for…

Machine Learning · Computer Science 2022-05-25 Ben Zhang , Zhetong Dong , Junsong Zhang , Hongwei Lin

Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. However, in the presence of many downstream tasks, fine-tuning is parameter inefficient: an entire new model is required for every task. As an alternative, we…

Attention based Transformer architecture has enabled significant advances in the field of natural language processing. In addition to new pre-training techniques, recent improvements crucially rely on working with a relatively larger…

Machine Learning · Computer Science 2020-02-18 Srinadh Bhojanapalli , Chulhee Yun , Ankit Singh Rawat , Sashank J. Reddi , Sanjiv Kumar

In the last decade, a considerable research effort has been devoted to developing adaptive algorithms based on kernel functions. One of the main features of these algorithms is that they form a family of universal approximation techniques,…

Signal Processing · Electrical Eng. & Systems 2018-08-21 A. Flores , R. C. de Lamare