English
Related papers

Related papers: Rethinking Positional Encoding in Language Pre-tra…

200 papers

Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness of position-based addressing. Many current methods enforce…

Computation and Language · Computer Science 2025-08-22 Jiajun Zhu , Peihao Wang , Ruisi Cai , Jason D. Lee , Pan Li , Zhangyang Wang

Positional Encodings (PEs) are used to inject word-order information into transformer-based language models. While they can significantly enhance the quality of sentence representations, their specific contribution to language models is not…

Computation and Language · Computer Science 2023-10-20 Lihu Chen , Gaël Varoquaux , Fabian M. Suchanek

Position encoding (PE), an essential part of self-attention networks (SANs), is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences. However, in…

Computation and Language · Computer Science 2020-11-24 Liang Ding , Longyue Wang , Dacheng Tao

The attention mechanism is a critical component of Large Language Models (LLMs) that allows tokens in a sequence to interact with each other, but is order-invariant. Incorporating position encoding (PE) makes it possible to address by…

Computation and Language · Computer Science 2024-05-31 Olga Golovneva , Tianlu Wang , Jason Weston , Sainbayar Sukhbaatar

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Mouxiao Huang , Borui Jiang , Dehua Zheng , Hailin Hu , Kai Han , Xinghao Chen

Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various…

Computation and Language · Computer Science 2023-11-09 Jianlin Su , Yu Lu , Shengfeng Pan , Ahmed Murtadha , Bo Wen , Yunfeng Liu

Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding tasks. By supplementing language model-style pretraining with further training on…

Computation and Language · Computer Science 2019-03-01 Jason Phang , Thibault Févry , Samuel R. Bowman

Transformer architecture has enabled recent progress in speech enhancement. Since Transformers are position-agostic, positional encoding is the de facto standard component used to enable Transformers to distinguish the order of elements in…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-15 Qiquan Zhang , Meng Ge , Hongxu Zhu , Eliathamby Ambikairajah , Qi Song , Zhaoheng Ni , Haizhou Li

Due to the complex layouts of documents, it is challenging to extract information for documents. Most previous studies develop multimodal pre-trained models in a self-supervised way. In this paper, we focus on the embedding learning of word…

Computation and Language · Computer Science 2022-08-01 Song Tao , Zijian Wang , Tiantian Fan , Canjie Luo , Can Huang

Language Models (LMs) have shown state-of-the-art performance in Natural Language Processing (NLP) tasks. Downstream tasks such as Named Entity Recognition (NER) or Part-of-Speech (POS) tagging are known to suffer from data imbalance…

Computation and Language · Computer Science 2024-04-12 Mehdi Ben Amor , Michael Granitzer , Jelena Mitrović

There are several improvements proposed over the baseline Absolute Positional Encoding (APE) method used in original transformer. In this study, we aim to investigate the implications of inadequately representing positional encoding in…

Computation and Language · Computer Science 2024-05-09 Arpit Aggarwal

Transformer language models encode the notion of word order using positional information. Most commonly, this positional information is represented by absolute position embeddings (APEs), that are learned from the pretraining data. However,…

Computation and Language · Computer Science 2022-10-25 Koustuv Sinha , Amirhossein Kazemnejad , Siva Reddy , Joelle Pineau , Dieuwke Hupkes , Adina Williams

Recurrent models have been dominating the field of neural machine translation (NMT) for the past few years. Transformers \citep{vaswani2017attention}, have radically changed it by proposing a novel architecture that relies on a feed-forward…

Computation and Language · Computer Science 2022-10-25 Joyce Zheng , Mehdi Rezagholizadeh , Peyman Passban

In this work, we revisit the Transformer-based pre-trained language models and identify two different types of information confusion in position encoding and model representations, respectively. Firstly, we show that in the relative…

Computation and Language · Computer Science 2023-02-10 Haojie Zhang , Mingfei Liang , Ruobing Xie , Zhenlong Sun , Bo Zhang , Leyu Lin

Transformer has demonstrated its great power to learn contextual word representations for multiple languages in a single model. To process multilingual sentences in the model, a learnable vector is usually assigned to each language, which…

Computation and Language · Computer Science 2021-02-17 Shengjie Luo , Kaiyuan Gao , Shuxin Zheng , Guolin Ke , Di He , Liwei Wang , Tie-Yan Liu

Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically…

Computation and Language · Computer Science 2022-04-20 Ziyang Luo , Yadong Xi , Jing Ma , Zhiwei Yang , Xiaoxi Mao , Changjie Fan , Rongsheng Zhang

Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-20 Jingru Lin , Xianghu Yue , Junyi Ao , Haizhou Li

Positional encodings enable Transformers to incorporate sequential information, yet their theoretical understanding remains limited to two properties: distance attenuation and translation invariance. Because natural language lacks purely…

Machine Learning · Computer Science 2026-02-11 Zihan Gu , Ruoyu Chen , Han Zhang , Hua Zhang , Yue Hu

Without positional information, attention-based Transformer neural networks are permutation-invariant. Absolute or relative positional embeddings are the most popular ways to feed Transformer models with positional information. Absolute…

Machine Learning · Computer Science 2021-11-10 Tatiana Likhomanenko , Qiantong Xu , Gabriel Synnaeve , Ronan Collobert , Alex Rogozhnikov

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

Computation and Language · Computer Science 2015-08-04 Jian Tang , Meng Qu , Qiaozhu Mei
‹ Prev 1 2 3 10 Next ›