English
Related papers

Related papers: SkillNet-NLU: A Sparsely Activated Model for Gener…

200 papers

Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning on multilingual…

Computation and Language · Computer Science 2022-04-07 Yanyang Li , Fuli Luo , Runxin Xu , Songfang Huang , Fei Huang , Liwei Wang

This paper explores the task Natural Language Understanding (NLU) by looking at duplicate question detection in the Quora dataset. We conducted extensive exploration of the dataset and used various machine learning models, including linear…

Computation and Language · Computer Science 2019-07-03 Lakshay Sharma , Laura Graesser , Nikita Nangia , Utku Evci

Large-scale pre-trained language models have shown impressive results on language understanding benchmarks like GLUE and SuperGLUE, improving considerably over other pre-training methods like distributed representations (GloVe) and purely…

Computation and Language · Computer Science 2020-05-12 Tanja Bunk , Daksh Varshneya , Vladimir Vlasov , Alan Nichol

Recently deep learning has dominated many machine learning areas, including spoken language understanding (SLU). However, deep learning models are notorious for being data-hungry, and the heavily optimized models are usually sensitive to…

Computation and Language · Computer Science 2020-12-15 Shang-Wen Li , Jason Krone , Shuyan Dong , Yi Zhang , Yaser Al-onaizan

Deep learning models have achieved remarkable success in natural language inference (NLI) tasks. While these models are widely explored, they are hard to interpret and it is often unclear how and why they actually work. In this paper, we…

Computation and Language · Computer Science 2019-05-21 Reza Ghaeini , Xiaoli Z. Fern , Prasad Tadepalli

Speech representations learned from Self-supervised learning (SSL) models can benefit various speech processing tasks. However, utilizing SSL representations usually requires fine-tuning the pre-trained models or designing task-specific…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-12 Kai-Wei Chang , Wei-Cheng Tseng , Shang-Wen Li , Hung-yi Lee

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…

Computation and Language · Computer Science 2021-09-06 Paul Michel

Structured pruning is widely used to compress large language models (LLMs), yet its effectiveness depends heavily on neuron importance estimation. Most existing methods estimate neuron importance from activation statistics on a single…

Machine Learning · Computer Science 2026-03-17 Xiaoyun Liu , Divya Saxena , Jiannong Cao , Yuqing Zhao , Yiying Dong , Penghui Ruan

Fine-tuning large pre-trained models with task-specific data has achieved great success in NLP. However, it has been demonstrated that the majority of information within the self-attention networks is redundant and not utilized effectively…

Computation and Language · Computer Science 2021-06-02 Jiaao Chen , Dinghan Shen , Weizhu Chen , Diyi Yang

Large language models (LLMs) have revolutionized natural language processing (NLP) by excelling at understanding and generating human-like text. However, their widespread deployment can be prohibitively expensive. SortedNet is a recent…

Computation and Language · Computer Science 2024-02-12 Parsa Kavehzadeh , Mojtaba Valipour , Marzieh Tahaei , Ali Ghodsi , Boxing Chen , Mehdi Rezagholizadeh

We present MT-DNN, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models. Built upon PyTorch and Transformers, MT-DNN is designed to facilitate…

Computation and Language · Computer Science 2020-05-19 Xiaodong Liu , Yu Wang , Jianshu Ji , Hao Cheng , Xueyun Zhu , Emmanuel Awa , Pengcheng He , Weizhu Chen , Hoifung Poon , Guihong Cao , Jianfeng Gao

Typically, machine learning systems solve new tasks by training on thousands of examples. In contrast, humans can solve new tasks by reading some instructions, with perhaps an example or two. To take a step toward closing this gap, we…

Computation and Language · Computer Science 2020-11-17 Orion Weller , Nicholas Lourie , Matt Gardner , Matthew E. Peters

We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the inactive neurons and…

Machine Learning · Computer Science 2019-03-12 Siavash Golkar , Michael Kagan , Kyunghyun Cho

Neural-based end-to-end approaches to natural language generation (NLG) from structured data or knowledge are data-hungry, making their adoption for real-world applications difficult with limited data. In this work, we propose the new task…

Computation and Language · Computer Science 2020-04-21 Zhiyu Chen , Harini Eavani , Wenhu Chen , Yinyin Liu , William Yang Wang

Natural language understanding (NLU) models often rely on dataset biases rather than intended task-relevant features to achieve high performance on specific datasets. As a result, these models perform poorly on datasets outside the training…

Computation and Language · Computer Science 2023-01-05 Yougang Lyu , Piji Li , Yechang Yang , Maarten de Rijke , Pengjie Ren , Yukun Zhao , Dawei Yin , Zhaochun Ren

Pre-trained language models have achieved huge improvement on many NLP tasks. However, these methods are usually designed for written text, so they do not consider the properties of spoken language. Therefore, this paper aims at…

Computation and Language · Computer Science 2020-11-03 Chao-Wei Huang , Yun-Nung Chen

The demand for efficient processing of deep neural networks (DNNs) on embedded devices is a significant challenge limiting their deployment. Exploiting sparsity in the network's feature maps is one of the ways to reduce its inference…

Computer Vision and Pattern Recognition · Computer Science 2023-09-28 Matteo Grimaldi , Darshan C. Ganji , Ivan Lazarevich , Sudhakar Sah

Large Language Models have become the core architecture upon which most modern natural language processing (NLP) systems build. These models can consistently deliver impressive accuracy and robustness across tasks and domains, but their…

Computation and Language · Computer Science 2023-04-07 Daniel Campos , Alexandre Marques , Tuan Nguyen , Mark Kurtz , ChengXiang Zhai

It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings. There is minimal theoretical understanding of empirical success, e.g., why fine-tuning a model with $10^8$ or more…

Machine Learning · Computer Science 2023-06-07 Sadhika Malladi , Alexander Wettig , Dingli Yu , Danqi Chen , Sanjeev Arora

Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM, that does not rely on large-scale…

Computation and Language · Computer Science 2022-07-25 Xingcheng Yao , Yanan Zheng , Xiaocong Yang , Zhilin Yang