English
Related papers

Related papers: Transformers without Tears: Improving the Normaliz…

200 papers

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution is to continually pre-train these models, saving significant…

End-to-end speech translation, a hot topic in recent years, aims to translate a segment of audio into a specific language with an end-to-end model. Conventional approaches employ multi-task learning and pre-training methods for this task,…

Computation and Language · Computer Science 2019-11-19 Chengyi Wang , Yu Wu , Shujie Liu , Zhenglu Yang , Ming Zhou

Although transformer-based models have shown exceptional empirical performance, the fundamental principles governing their training dynamics are inadequately characterized beyond configuration-specific studies. Inspired by empirical…

Machine Learning · Computer Science 2025-10-09 Zheng-An Chen , Tao Luo

Including memory banks in a natural language processing architecture increases model capacity by equipping it with additional data at inference time. In this paper, we build upon $k$NN-LM \citep{khandelwal20generalization}, which uses a…

Computation and Language · Computer Science 2021-09-20 Jean-Francois Ton , Walter Talbott , Shuangfei Zhai , Josh Susskind

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

State-of-the-art LLMs often rely on scale with high computational costs, which has sparked a research agenda to reduce parameter counts and costs without significantly impacting performance. Our study focuses on Transformer-based LLMs,…

Computation and Language · Computer Science 2024-07-25 Xiuying Wei , Skander Moalla , Razvan Pascanu , Caglar Gulcehre

Despite being the current de-facto models in most NLP tasks, transformers are often limited to short sequences due to their quadratic attention complexity on the number of tokens. Several attempts to address this issue were studied, either…

Computation and Language · Computer Science 2023-07-19 Amine Abdaoui , Sourav Dutta

The Transformer architecture has led to significant gains in machine translation. However, most studies focus on only sentence-level translation without considering the context dependency within documents, leading to the inadequacy of…

Artificial Intelligence · Computer Science 2022-10-21 Yukun Feng , Feng Li , Ziang Song , Boyuan Zheng , Philipp Koehn

Increasing the input length has been a driver of progress in language modeling with transformers. We identify conditions where shorter inputs are not harmful, and achieve perplexity and efficiency improvements through two new methods that…

Computation and Language · Computer Science 2021-06-04 Ofir Press , Noah A. Smith , Mike Lewis

Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a…

Machine Learning · Computer Science 2019-06-04 Zihang Dai , Zhilin Yang , Yiming Yang , Jaime Carbonell , Quoc V. Le , Ruslan Salakhutdinov

Fine-tuning pre-trained language models (PTLMs), such as BERT and its better variant RoBERTa, has been a common practice for advancing performance in natural language understanding (NLU) tasks. Recent advance in representation learning…

Computation and Language · Computer Science 2021-02-05 Wenxuan Zhou , Bill Yuchen Lin , Xiang Ren

Training stability of large language models(LLMs) is an important research topic. Reproducing training instabilities can be costly, so we use a small language model with 830M parameters and experiment with higher learning rates to force…

Computation and Language · Computer Science 2024-10-23 Oleg Rybakov , Mike Chrzanowski , Peter Dykas , Jinze Xue , Ben Lanir

We present TransNormerLLM, the first linear attention-based Large Language Model (LLM) that outperforms conventional softmax attention-based models in terms of both accuracy and efficiency. TransNormerLLM evolves from the previous linear…

Computation and Language · Computer Science 2024-01-22 Zhen Qin , Dong Li , Weigao Sun , Weixuan Sun , Xuyang Shen , Xiaodong Han , Yunshen Wei , Baohong Lv , Xiao Luo , Yu Qiao , Yiran Zhong

Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only…

Computation and Language · Computer Science 2021-09-16 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

Conventional fine-tuning encounters increasing difficulties given the size of current Pre-trained Language Models, which makes parameter-efficient tuning become the focal point of frontier research. Previous methods in this field add…

Computation and Language · Computer Science 2022-12-12 Wang Qi , Yu-Ping Ruan , Yuan Zuo , Taihao Li

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges…

Computation and Language · Computer Science 2020-04-07 Wenhui Wang , Furu Wei , Li Dong , Hangbo Bao , Nan Yang , Ming Zhou

This work presents a general unsupervised learning method to improve the accuracy of sequence to sequence (seq2seq) models. In our method, the weights of the encoder and decoder of a seq2seq model are initialized with the pretrained weights…

Computation and Language · Computer Science 2018-02-23 Prajit Ramachandran , Peter J. Liu , Quoc V. Le

Transformers have outperformed recurrent neural networks (RNNs) in natural language generation. But this comes with a significant computational cost, as the attention mechanism's complexity scales quadratically with sequence length.…

Computation and Language · Computer Science 2021-09-21 Jungo Kasai , Hao Peng , Yizhe Zhang , Dani Yogatama , Gabriel Ilharco , Nikolaos Pappas , Yi Mao , Weizhu Chen , Noah A. Smith

Transformer models using segment-based processing have been an effective architecture for simultaneous speech translation. However, such models create a context mismatch between training and inference environments, hindering potential…

Computation and Language · Computer Science 2023-07-06 Matthew Raffel , Drew Penney , Lizhong Chen

The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks. To address this issue, parameter-efficient transfer learning methods have been proposed to…

Computation and Language · Computer Science 2022-10-27 Yifan Chen , Devamanyu Hazarika , Mahdi Namazifar , Yang Liu , Di Jin , Dilek Hakkani-Tur