English
Related papers

Related papers: Modeling Recurrence for Transformer

200 papers

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

Machine Learning · Computer Science 2026-04-24 Costin-Andrei Oncescu , Depen Morwani , Samy Jelassi , Alexandru Meterez , Mujin Kwun , Sham Kakade

Transformer networks have lead to important progress in language modeling and machine translation. These models include two consecutive modules, a feed-forward layer and a self-attention layer. The latter allows the network to capture long…

Machine Learning · Computer Science 2019-07-03 Sainbayar Sukhbaatar , Edouard Grave , Guillaume Lample , Herve Jegou , Armand Joulin

Recurrent neural networks (RNNs) have represented for years the state of the art in neural machine translation. Recently, new architectures have been proposed, which can leverage parallel computation on GPUs better than classical RNNs.…

Computation and Language · Computer Science 2018-05-14 Mattia Antonino Di Gangi , Marcello Federico

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

Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and local information has…

Computation and Language · Computer Science 2022-12-09 Aydar Bulatov , Yuri Kuratov , Mikhail S. Burtsev

Attention mechanism has enhanced state-of-the-art Neural Machine Translation (NMT) by jointly learning to align and translate. It tends to ignore past alignment information, however, which often leads to over-translation and…

Computation and Language · Computer Science 2016-08-09 Zhaopeng Tu , Zhengdong Lu , Yang Liu , Xiaohua Liu , Hang Li

In this work, we propose Retentive Network (RetNet) as a foundation architecture for large language models, simultaneously achieving training parallelism, low-cost inference, and good performance. We theoretically derive the connection…

Computation and Language · Computer Science 2023-08-10 Yutao Sun , Li Dong , Shaohan Huang , Shuming Ma , Yuqing Xia , Jilong Xue , Jianyong Wang , Furu Wei

The dominant neural machine translation models are based on the encoder-decoder structure, and many of them rely on an unconstrained receptive field over source and target sequences. In this paper we study a new architecture that breaks…

Computation and Language · Computer Science 2019-05-17 José A. R. Fonollosa , Noe Casas , Marta R. Costa-jussà

Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each…

Computation and Language · Computer Science 2018-10-02 Lesly Miculicich Werlen , Nikolaos Pappas , Dhananjay Ram , Andrei Popescu-Belis

This research presents a fine-grained human evaluation to compare the Transformer and recurrent approaches to neural machine translation (MT), on the translation direction English-to-Chinese. To this end, we develop an error taxonomy…

Computation and Language · Computer Science 2020-06-16 Yuying Ye , Antonio Toral

In this paper, we enhance the attention-based neural machine translation (NMT) by adding explicit coverage embedding models to alleviate issues of repeating and dropping translations in NMT. For each source word, our model starts with a…

Computation and Language · Computer Science 2016-08-30 Haitao Mi , Baskaran Sankaran , Zhiguo Wang , Abe Ittycheriah

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Computation and Language · Computer Science 2024-10-18 Ruiqing Yan , Linghan Zheng , Xingbo Du , Han Zou , Yufeng Guo , Jianfei Yang

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Computation and Language · Computer Science 2023-05-17 Nurullah Sevim , Ege Ozan Özyedek , Furkan Şahinuç , Aykut Koç

Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…

Computation and Language · Computer Science 2020-10-06 Alessandro Raganato , Yves Scherrer , Jörg Tiedemann

The architecture of Transformer is based entirely on self-attention, and has been shown to outperform models that employ recurrence on sequence transduction tasks such as machine translation. The superior performance of Transformer has been…

Machine Learning · Computer Science 2019-08-29 Vikas K. Garg , Inderjit S. Dhillon , Hsiang-Fu Yu

Neural Machine Translation model is a sequence-to-sequence converter based on neural networks. Existing models use recurrent neural networks to construct both the encoder and decoder modules. In alternative research, the recurrent networks…

Computation and Language · Computer Science 2021-05-04 Ritam Mallick , Seba Susan , Vaibhaw Agrawal , Rizul Garg , Prateek Rawal

In this work, we explore whether modeling recurrence into the Transformer architecture can both be beneficial and efficient, by building an extremely simple recurrent module into the Transformer. We compare our model to baselines following…

Computation and Language · Computer Science 2022-05-25 Tao Lei , Ran Tian , Jasmijn Bastings , Ankur P. Parikh

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies. However, it calculates the dependencies between representations without considering the…

Computation and Language · Computer Science 2019-02-18 Baosong Yang , Jian Li , Derek Wong , Lidia S. Chao , Xing Wang , Zhaopeng Tu

Transformer-based deep learning models have achieved state-of-the-art performance across numerous language and vision tasks. While the self-attention mechanism, a core component of transformers, has proven capable of handling complex data…

Machine Learning · Computer Science 2025-08-05 Laziz Abdullaev , Tan M. Nguyen

Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the…

Computation and Language · Computer Science 2019-09-06 Chengyi Wang , Shuangzhi Wu , Shujie Liu