English
Related papers

Related papers: The Case for Translation-Invariant Self-Attention …

200 papers

An ideal length-extrapolatable Transformer language model can handle sequences longer than the training length without any fine-tuning. Such long-context utilization capability relies heavily on a flexible positional embedding design. Upon…

Computation and Language · Computer Science 2023-11-16 Ta-Chung Chi , Ting-Han Fan , Alexander I. Rudnicky

Transformers are arguably the main workhorse in recent Natural Language Processing research. By definition a Transformer is invariant with respect to reordering of the input. However, language is inherently sequential and word order is…

Computation and Language · Computer Science 2021-09-10 Philipp Dufter , Martin Schmitt , Hinrich Schütze

Self-attention is essential to Transformer architectures, yet how information is embedded in the self-attention matrices and how different objective functions impact this process remains unclear. We present a mathematical framework to…

Machine Learning · Computer Science 2025-06-04 Matteo Saponati , Pascal Sager , Pau Vilimelis Aceituno , Thilo Stadelmann , Benjamin Grewe

In Transformer-based neural machine translation (NMT), the positional encoding mechanism helps the self-attention networks to learn the source representation with order dependency, which makes the Transformer-based NMT achieve…

Computation and Language · Computer Science 2020-04-09 Kehai Chen , Rui Wang , Masao Utiyama , Eiichiro Sumita

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

Large language models (LLMs) exhibit remarkable performance improvement through in-context learning (ICL) by leveraging task-specific examples in the input. However, the mechanisms behind this improvement remain elusive. In this work, we…

Computation and Language · Computer Science 2024-02-23 Safoora Yousefi , Leo Betthauser , Hosein Hasanbeig , Raphaël Millière , Ida Momennejad

Given the rapidly evolving nature of social media and people's views, word usage changes over time. Consequently, the performance of a classifier trained on old textual data can drop dramatically when tested on newer data. While research in…

Computation and Language · Computer Science 2021-08-31 Rabab Alkhalifa , Elena Kochkina , Arkaitz Zubiaga

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive…

Machine Learning · Computer Science 2022-09-21 Timo Lohrenz , Björn Möller , Zhengyang Li , Tim Fingscheidt

This paper describes how to apply self-attention with relative positional encodings to the task of relation extraction. We propose to use the self-attention encoder layer together with an additional position-aware attention layer that takes…

Computation and Language · Computer Science 2018-07-10 Ivan Bilan , Benjamin Roth

Transformer models have become foundational across a wide range of scientific and engineering domains due to their strong empirical performance. A key capability underlying their success is in-context learning (ICL): when presented with a…

Machine Learning · Computer Science 2026-04-29 Zhen Qin , Jiachen Jiang , Zhihui Zhu

Creating meta-embeddings for better performance in language modelling has received attention lately, and methods based on concatenation or merely calculating the arithmetic mean of more than one separately trained embeddings to perform…

Computation and Language · Computer Science 2020-07-03 Qichen Li , Yuanqing Lin , Luofeng Zhou , Jian Li

We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model long-context. RoPE extension methods may alleviate this…

Computation and Language · Computer Science 2026-05-12 Yu Wang , Sheng Shen , Rémi Munos , Hongyuan Zhan , Yuandong Tian

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

Computation and Language · Computer Science 2023-02-09 Hongqiu Wu , Ruixue Ding , Hai Zhao , Pengjun Xie , Fei Huang , Min Zhang

Pretrained language models based on the transformer architecture have shown great success in NLP. Textual training data often comes from the web and is thus tagged with time-specific information, but most language models ignore this…

Computation and Language · Computer Science 2022-05-05 Guy D. Rosin , Kira Radinsky

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

The attention mechanism within the transformer architecture enables the model to weigh and combine tokens based on their relevance to the query. While self-attention has enjoyed major success, it notably treats all queries $q$ in the same…

Machine Learning · Computer Science 2024-11-21 Xuechen Zhang , Xiangyu Chang , Mingchen Li , Amit Roy-Chowdhury , Jiasi Chen , Samet Oymak

Neural encoder-decoder models of machine translation have achieved impressive results, rivalling traditional translation models. However their modelling formulation is overly simplistic, and omits several key inductive biases built into…

Computation and Language · Computer Science 2016-01-07 Trevor Cohn , Cong Duy Vu Hoang , Ekaterina Vymolova , Kaisheng Yao , Chris Dyer , Gholamreza Haffari

Transformer-based language models have achieved impressive success in various natural language processing tasks due to their ability to capture complex dependencies and contextual information using self-attention mechanisms. However, they…

Computation and Language · Computer Science 2023-06-26 Kaushik Roy , Yuxin Zi , Vignesh Narayanan , Manas Gaur , Amit Sheth

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 encoder-decoder is the typical framework for Neural Machine Translation (NMT), and different structures have been developed for improving the translation performance. Transformer is one of the most promising structures, which can…

Computation and Language · Computer Science 2018-12-11 Kaitao Song , Xu Tan , Furong Peng , Jianfeng Lu