English
Related papers

Related papers: Multiplicative Position-aware Transformer Models f…

200 papers

The Transformer translation model (Vaswani et al., 2017) based on a multi-head attention mechanism can be computed effectively in parallel and has significantly pushed forward the performance of Neural Machine Translation (NMT). Though…

Computation and Language · Computer Science 2020-06-26 Hongfei Xu , Josef van Genabith , Deyi Xiong , Qiuhui Liu , Jingyi Zhang

Multilayer transformer networks consist of interleaved self-attention and feedforward sublayers. Could ordering the sublayers in a different pattern lead to better performance? We generate randomly ordered transformers and train them with…

Computation and Language · Computer Science 2020-04-24 Ofir Press , Noah A. Smith , Omer Levy

Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while `multi-sense' methods have been proposed and tested on artificial…

Computation and Language · Computer Science 2015-11-25 Jiwei Li , Dan Jurafsky

The Position Embedding (PE) is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operation. By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization,…

Computer Vision and Pattern Recognition · Computer Science 2022-12-23 Runyi Yu , Zhennan Wang , Yinhuai Wang , Kehan Li , Yian Zhao , Jian Zhang , Guoli Song , Jie Chen

In this paper, we try to understand neural machine translation (NMT) via simplifying NMT architectures and training encoder-free NMT models. In an encoder-free model, the sums of word embeddings and positional embeddings represent the…

Computation and Language · Computer Science 2019-07-19 Gongbo Tang , Rico Sennrich , Joakim Nivre

There are massive amounts of textual data residing in databases, valuable for many machine learning (ML) tasks. Since ML techniques depend on numerical input representations, word embeddings are increasingly utilized to convert symbolic…

Databases · Computer Science 2020-01-23 Michael Günther , Maik Thiele , Wolfgang Lehner

There is a growing interest in the ability of neural networks to execute algorithmic tasks (e.g., arithmetic, summary statistics, and sorting). The goal of this work is to better understand the role of attention in Transformers for…

Machine Learning · Computer Science 2025-06-11 Artur Back de Luca , George Giapitzakis , Shenghao Yang , Petar Veličković , Kimon Fountoulakis

This position paper argues that text embedding research should move beyond surface meaning and embrace implicit semantics as a central modeling objective. Text embeddings are a foundational component of modern NLP, underpinning a wide range…

Computation and Language · Computer Science 2026-05-29 Yiqun Sun , Qiang Huang , Anthony K. H. Tung , Jun Yu

Over the last two decades we have witnessed strong progress on modeling visual object classes, scenes and attributes that have significantly contributed to automated image understanding. On the other hand, surprisingly little progress has…

Computer Vision and Pattern Recognition · Computer Science 2015-05-06 Mateusz Malinowski , Mario Fritz

Knowledge bases, and their representations in the form of knowledge graphs (KGs), are naturally incomplete. Since scientific and industrial applications have extensively adopted them, there is a high demand for solutions that complete their…

Artificial Intelligence · Computer Science 2025-07-30 Vítor Lourenço , Aline Paes

Large-scale learning of transformer language models has yielded improvements on a variety of natural language understanding tasks. Whether they can be effectively adapted for summarization, however, has been less explored, as the learned…

Computation and Language · Computer Science 2019-06-04 Andrew Hoang , Antoine Bosselut , Asli Celikyilmaz , Yejin Choi

Operator learning for Partial Differential Equations (PDEs) is rapidly emerging as a promising approach for surrogate modeling of intricate systems. Transformers with the self-attention mechanism$\unicode{x2013}$a powerful tool originally…

Machine Learning · Computer Science 2024-05-17 Junfeng Chen , Kailiang Wu

The recent success of transformer networks for neural machine translation and other NLP tasks has led to a surge in research work trying to apply it for speech recognition. Recent efforts studied key research questions around ways of…

Computation and Language · Computer Science 2020-03-04 Abdelrahman Mohamed , Dmytro Okhonko , Luke Zettlemoyer

Pretrained embeddings based on the Transformer architecture have taken the NLP community by storm. We show that they can mathematically be reframed as a sum of vector factors and showcase how to use this reframing to study the impact of…

Computation and Language · Computer Science 2022-06-09 Timothee Mickus , Denis Paperno , Mathieu Constant

The Transformer based neural networks have been showing significant advantages on most evaluations of various natural language processing and other sequence-to-sequence tasks due to its inherent architecture based superiorities. Although…

Computation and Language · Computer Science 2019-10-31 Hailiang Li , Adele Y. C. Wang , Yang Liu , Du Tang , Zhibin Lei , Wenye Li

Embedding matrices are key components in neural natural language processing (NLP) models that are responsible to provide numerical representations of input tokens.\footnote{In this paper words and subwords are referred to as \textit{tokens}…

Computation and Language · Computer Science 2022-04-19 Krtin Kumar , Peyman Passban , Mehdi Rezagholizadeh , Yiu Sing Lau , Qun Liu

The multi-head self-attention mechanism of the transformer model has been thoroughly investigated recently. In one vein of study, researchers are interested in understanding why and how transformers work. In another vein, researchers…

Computation and Language · Computer Science 2022-10-28 Raymond Li , Wen Xiao , Linzi Xing , Lanjun Wang , Gabriel Murray , Giuseppe Carenini

In the Transformer model, "self-attention" combines information from attended embeddings into the representation of the focal embedding in the next layer. Thus, across layers of the Transformer, information originating from different tokens…

Machine Learning · Computer Science 2020-06-02 Samira Abnar , Willem Zuidema

A promising approach to preserving model performance in linearized transformers is to employ position-based re-weighting functions. However, state-of-the-art re-weighting functions rely heavily on target sequence lengths, making it…

Computation and Language · Computer Science 2024-05-24 Victor Agostinelli , Sanghyun Hong , Lizhong Chen

In this paper, we propose an efficient transformer architecture that uses reinforced positional embedding to obtain superior performance with half the number of encoder decoder layers. We demonstrate that concatenating positional encoding…

Computation and Language · Computer Science 2024-10-08 Yen-Che Hsiao , Abhishek Dutta