English
Related papers

Related papers: Pruning and Sparsemax Methods for Hierarchical Att…

200 papers

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

We propose a new self-organizing hierarchical softmax formulation for neural-network-based language models over large vocabularies. Instead of using a predefined hierarchical structure, our approach is capable of learning word clusters with…

Computation and Language · Computer Science 2017-07-29 Yikang Shen , Shawn Tan , Chrisopher Pal , Aaron Courville

Self-supervised speech representation learning (speech SSL) has demonstrated the benefit of scale in learning rich representations for Automatic Speech Recognition (ASR) with limited paired data, such as wav2vec 2.0. We investigate the…

Computation and Language · Computer Science 2021-10-27 Cheng-I Jeff Lai , Yang Zhang , Alexander H. Liu , Shiyu Chang , Yi-Lun Liao , Yung-Sung Chuang , Kaizhi Qian , Sameer Khurana , David Cox , James Glass

This paper proposes Attention-Seeker, an unsupervised keyphrase extraction method that leverages self-attention maps from a Large Language Model to estimate the importance of candidate phrases. Our approach identifies specific components -…

Computation and Language · Computer Science 2024-12-17 Erwin D. López Z. , Cheng Tang , Atsushi Shimada

With the advent of word embeddings, lexicons are no longer fully utilized for sentiment analysis although they still provide important features in the traditional setting. This paper introduces a novel approach to sentiment analysis that…

Computation and Language · Computer Science 2017-08-24 Bonggun Shin , Timothy Lee , Jinho D. Choi

Pre-trained language models (PLMs) are engineered to be robust in contextual understanding and exhibit outstanding performance in various natural language processing tasks. However, their considerable size incurs significant computational…

Computation and Language · Computer Science 2024-08-21 Guanchen Li , Xiandong Zhao , Lian Liu , Zeping Li , Dong Li , Lu Tian , Jie He , Ashish Sirasao , Emad Barsoum

The transformative impact of large language models (LLMs) like LLaMA and GPT on natural language processing is countered by their prohibitive computational demands. Pruning has emerged as a pivotal compression strategy, introducing sparsity…

Computation and Language · Computer Science 2024-11-04 Guangji Bai , Yijiang Li , Chen Ling , Kibaek Kim , Liang Zhao

Large language models (LLMs) face significant deployment challenges due to their massive computational demands. % While pruning offers a promising compression solution, existing methods suffer from two critical limitations: (1) They neglect…

Machine Learning · Computer Science 2026-04-01 Lang Xiong , Ning Liu , Ao Ren , Yuheng Bai , Haining Fang , BinYan Zhang , Zhe Jiang , Yujuan Tan , Duo Liu

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

Machine Learning · Computer Science 2026-04-17 Dongsheng Wang , Jinsen Zhang , Dawei Su , Hui Huang

In aspect-level sentiment classification (ASC), it is prevalent to equip dominant neural models with attention mechanisms, for the sake of acquiring the importance of each context word on the given aspect. However, such a mechanism tends to…

Computation and Language · Computer Science 2019-06-07 Jialong Tang , Ziyao Lu , Jinsong Su , Yubin Ge , Linfeng Song , Le Sun , Jiebo Luo

Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does…

Machine Learning · Statistics 2018-11-09 Yuntian Deng , Yoon Kim , Justin Chiu , Demi Guo , Alexander M. Rush

Transformers and their attention mechanism have been revolutionary in the field of Machine Learning. While originally proposed for the language data, they quickly found their way to the image, video, graph, etc. data modalities with various…

Machine Learning · Computer Science 2025-09-22 Saeed Amizadeh , Sara Abdali , Yinheng Li , Kazuhito Koishida

Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work has shown, however, that a large proportion of the heads in…

Computation and Language · Computer Science 2023-07-28 Jiaoda Li , Ryan Cotterell , Mrinmaya Sachan

Pruning provides a practical solution to reduce the resources required to run large language models (LLMs) to benefit from their effective capabilities as well as control their cost for training and inference. Research on LLM pruning often…

Computation and Language · Computer Science 2025-10-28 Yuanhe Tian , Junjie Liu , Xican Yang , Haishan Ye , Yan Song

While Transformer-based models have shown impressive language modeling performance, the large computation cost is often prohibitive for practical use. Attention head pruning, which removes unnecessary attention heads in the multihead…

Computation and Language · Computer Science 2021-10-08 Kyuhong Shim , Iksoo Choi , Wonyong Sung , Jungwook Choi

Artificial neural networks (ANNs) especially deep convolutional networks are very popular these days and have been proved to successfully offer quite reliable solutions to many vision problems. However, the use of deep neural networks is…

Machine Learning · Computer Science 2020-07-28 Yangzi Guo , Yiyuan She , Adrian Barbu

Semantic matching is of central significance to the answer selection task which aims to select correct answers for a given question from a candidate answer pool. A useful method is to employ neural networks with attention to generate…

Computation and Language · Computer Science 2021-05-10 Jie Huang

Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applications. This is a potential issue because of the great amount of computational resources needed for training, and of the possible loss of…

Computation and Language · Computer Science 2022-10-31 Giovanni Bonetta , Matteo Ribero , Rossella Cancelliere

Despite the strong performance of Transformers, their quadratic computation complexity presents challenges in applying them to vision tasks. Automatic pruning is one of effective methods for reducing computation complexity without heuristic…

Computer Vision and Pattern Recognition · Computer Science 2024-06-03 Eunho Lee , Youngbae Hwang

We introduce Speech Information Retrieval (SIR), a new long-context task for Speech Large Language Models (Speech LLMs), and present SPIRAL, a 1,012-sample benchmark testing models' ability to extract critical details from approximately…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-01 Yueqian Lin , Yuzhe Fu , Jingyang Zhang , Yudong Liu , Jianyi Zhang , Jingwei Sun , Hai "Helen" Li , Yiran Chen