English
Related papers

Related papers: Improving Word Embedding Factorization for Compres…

200 papers

Word embeddings are the interface between the world of discrete units of text processing and the continuous, differentiable world of neural networks. In this work, we examine various random and pretrained initialization methods for…

Computation and Language · Computer Science 2017-11-28 Tom Kocmi , Ondřej Bojar

Topic modeling is a dominant method for exploring document collections on the web and in digital libraries. Recent approaches to topic modeling use pretrained contextualized language models and variational autoencoders. However, large…

Computation and Language · Computer Science 2024-06-21 Suman Adhya , Debarshi Kumar Sanyal

Knowledge Distillation (KD) is increasingly adopted to transfer capabilities from large language models to smaller ones, offering significant improvements in efficiency and utility while often surpassing standard fine-tuning. Beyond…

We propose a scalable tensorization framework for neural network compression based on slice-wise feature distillation. Unlike conventional tensor decomposition methods that rely on costly global finetuning, our approach decomposes the…

Machine Learning · Computer Science 2026-05-20 Safa Hamreras , Sukhbinder Singh , Román Orús

Text encoding is one of the most important steps in Natural Language Processing (NLP). It has been done well by the self-attention mechanism in the current state-of-the-art Transformer encoder, which has brought about significant…

Computation and Language · Computer Science 2021-02-12 Zuchao Li , Zhuosheng Zhang , Hai Zhao , Rui Wang , Kehai Chen , Masao Utiyama , Eiichiro Sumita

Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it…

Computation and Language · Computer Science 2022-09-12 Asahi Ushio , Jose Camacho-Collados , Steven Schockaert

Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Jongoh Jeong , Hoyong Kwon , Minseok Kim , Kuk-Jin Yoon

Pre-trained language models have demonstrated superior performance in various natural language processing tasks. However, these models usually contain hundreds of millions of parameters, which limits their practicality because of latency…

Computation and Language · Computer Science 2022-05-02 Simiao Zuo , Qingru Zhang , Chen Liang , Pengcheng He , Tuo Zhao , Weizhu Chen

Wavelet transforms, a powerful mathematical tool, have been widely used in different domains, including Signal and Image processing, to unravel intricate patterns, enhance data representation, and extract meaningful features from data.…

Computation and Language · Computer Science 2025-08-04 Rana Aref Salama , Abdou Youssef , Mona Diab

A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…

Computation and Language · Computer Science 2023-01-31 Jan Philip Wahle

Factorized layers--operations parameterized by products of two or more matrices--occur in a variety of deep learning contexts, including compressed model training, certain types of knowledge distillation, and multi-head self-attention…

Machine Learning · Statistics 2022-10-07 Mikhail Khodak , Neil Tenenholtz , Lester Mackey , Nicolò Fusi

Much of the focus in the area of knowledge distillation has been on distilling knowledge from a larger teacher network to a smaller student network. However, there has been little research on how the concept of distillation can be leveraged…

Neural and Evolutionary Computing · Computer Science 2019-01-29 Zhong Qiu Lin , Alexander Wong

We study the use of knowledge distillation to compress the U-net architecture. We show that, while standard distillation is not sufficient to reliably train a compressed U-net, introducing other regularization methods, such as batch…

Machine Learning · Computer Science 2018-12-04 Karttikeya Mangalam , Mathieu Salzamann

We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human…

Information Retrieval · Computer Science 2025-07-01 Chris Samarinas , Hamed Zamani

Embedding models have become essential tools in both natural language processing and computer vision, enabling efficient semantic search, recommendation, clustering, and more. However, the high memory and computational demands of…

Computation and Language · Computer Science 2024-11-26 Jiayi Chen , Chen Wu , Shaoqun Zhang , Nan Li , Liangjie Zhang , Qi Zhang

The notion of word embedding plays a fundamental role in natural language processing (NLP). However, pre-training word embedding for very large-scale vocabulary is computationally challenging for most existing methods. In this work, we show…

Computation and Language · Computer Science 2021-09-16 Junsheng Kong , Weizhao Li , Zeyi Liu , Ben Liao , Jiezhong Qiu , Chang-Yu Hsieh , Yi Cai , Shengyu Zhang

Pre-trained language models such as BERT have shown remarkable effectiveness in various natural language processing tasks. However, these models usually contain millions of parameters, which prevents them from practical deployment on…

Computation and Language · Computer Science 2022-01-03 Changsheng Zhao , Ting Hua , Yilin Shen , Qian Lou , Hongxia Jin

This work examines the possibility of using syllable embeddings, instead of the often used $n$-gram embeddings, as subword embeddings. We investigate this for two languages: English and Dutch. To this end, we also translated two standard…

Computation and Language · Computer Science 2022-01-14 Laurent Mertens , Joost Vennekens

Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such…

Computation and Language · Computer Science 2021-05-28 John Giorgi , Osvald Nitski , Bo Wang , Gary Bader

The large scale of pre-trained language models poses a challenge for their deployment on various devices, with a growing emphasis on methods to compress these models, particularly knowledge distillation. However, current knowledge…

Computation and Language · Computer Science 2023-06-13 Shicheng Tan , Weng Lam Tam , Yuanchun Wang , Wenwen Gong , Shu Zhao , Peng Zhang , Jie Tang