English
Related papers

Related papers: Deepening Hidden Representations from Pre-trained …

200 papers

It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…

Sound · Computer Science 2021-04-08 Marc-Antoine Georges , Laurent Girin , Jean-Luc Schwartz , Thomas Hueber

Modern data-driven machine learning system designs exploit inductive biases in architectural structure, invariance and equivariance requirements, task-specific loss functions, and computational optimization tools. Previous works have…

Neural and Evolutionary Computing · Computer Science 2025-03-04 Achref Jaziri , Sina Ditzel , Iuliia Pliushch , Visvanathan Ramesh

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

Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quality. However, existing methods universally extract features from only the last encoder…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Xuanyu Zhu , Yan Bai , Yang Shi , Yihang Lou , Yuanxing Zhang , Jing Jin , Yuan Zhou

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Computation and Language · Computer Science 2020-10-27 Hyung Won Chung , Thibault Févry , Henry Tsai , Melvin Johnson , Sebastian Ruder

The Transformer model has achieved state-of-the-art performance in many sequence modeling tasks. However, how to leverage model capacity with large or variable depths is still an open challenge. We present a probabilistic framework to…

Computation and Language · Computer Science 2020-10-19 Xian Li , Asa Cooper Stickland , Yuqing Tang , Xiang Kong

Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios. In this work, we present a novel method that operates on the hidden representations of a PLM to…

Computation and Language · Computer Science 2023-05-29 Linlin Liu , Xingxuan Li , Megh Thakkar , Xin Li , Shafiq Joty , Luo Si , Lidong Bing

We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features. We do this by: (i) the introduction of a perceptual…

Computer Vision and Pattern Recognition · Computer Science 2023-03-29 Samyakh Tukra , Frederick Hoffman , Ken Chatfield

Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even…

Machine Learning · Computer Science 2018-01-31 Łukasz Kaiser , Samy Bengio

Bidirectional Encoder Representations from Transformers (BERT) reach state-of-the-art results in a variety of Natural Language Processing tasks. However, understanding of their internal functioning is still insufficient and unsatisfactory.…

Computation and Language · Computer Science 2019-09-12 Betty van Aken , Benjamin Winter , Alexander Löser , Felix A. Gers

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…

Computation and Language · Computer Science 2021-09-22 Luyu Gao , Jamie Callan

Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Recently, an…

Machine Learning · Computer Science 2022-07-25 Konstantin Schürholt , Boris Knyazev , Xavier Giró-i-Nieto , Damian Borth

Representation of data on mixed variables, numerical and categorical types to get suitable feature map is a challenging task as important information lies in a complex non-linear manifold. The feature transformation should be able to…

Machine Learning · Computer Science 2020-09-22 Saswata Sahoo , Souradip Chakraborty

This study explores how bilingual language models develop complex internal representations. We employ sparse autoencoders to analyze internal representations of bilingual language models with a focus on the effects of training steps,…

Computation and Language · Computer Science 2025-10-13 Tatsuro Inaba , Go Kamoda , Kentaro Inui , Masaru Isonuma , Yusuke Miyao , Yohei Oseki , Benjamin Heinzerling , Yu Takagi

The pre-training of masked language models (MLMs) consumes massive computation to achieve good results on downstream NLP tasks, resulting in a large carbon footprint. In the vanilla MLM, the virtual tokens, [MASK]s, act as placeholders and…

Computation and Language · Computer Science 2022-11-16 Baohao Liao , David Thulke , Sanjika Hewavitharana , Hermann Ney , Christof Monz

Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream tasks. In this paper we explore whether it is possible to…

Computation and Language · Computer Science 2021-09-14 Xiongyi Zhang , Jan-Willem van de Meent , Byron C. Wallace

End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic…

Computation and Language · Computer Science 2021-05-12 Cheng Yi , Shiyu Zhou , Bo Xu

Recently, fine-tuning pre-trained code models such as CodeBERT on downstream tasks has achieved great success in many software testing and analysis tasks. While effective and prevalent, fine-tuning the pre-trained parameters incurs a large…

Software Engineering · Computer Science 2023-04-12 Ensheng Shi , Yanlin Wang , Hongyu Zhang , Lun Du , Shi Han , Dongmei Zhang , Hongbin Sun

Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…

Computation and Language · Computer Science 2020-02-06 Chi Sun , Xipeng Qiu , Yige Xu , Xuanjing Huang

In end-to-end speech translation, speech and text pre-trained models improve translation quality. Recently proposed models simply connect the pre-trained models of speech and text as encoder and decoder. Therefore, only the information from…

Computation and Language · Computer Science 2023-05-29 Yuta Nishikawa , Satoshi Nakamura