English
Related papers

Related papers: BERTQA -- Attention on Steroids

200 papers

The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. However, the quadratic computational complexity of MHA with…

Machine Learning · Computer Science 2025-10-03 Adam Filipek

Recent algebraic analysis shows that in decoder-only and encoder-only transformers, the Query projection $W_Q$ may be set to identity without noticeable performance deterioration. This is possible because attention depends on $X$ only…

Machine Learning · Computer Science 2026-05-27 Marko Karbevski

Relation extraction (RE) consists in identifying and structuring automatically relations of interest from texts. Recently, BERT improved the top performances for several NLP tasks, including RE. However, the best way to use BERT, within a…

Computation and Language · Computer Science 2020-11-26 Walid Hafiane , Joel Legrand , Yannick Toussaint , Adrien Coulet

Current state-of-the-art reading comprehension models rely heavily on recurrent neural networks. We explored an entirely different approach to question answering: a convolutional model. By their nature, these convolutional models are fast…

Computation and Language · Computer Science 2018-10-23 Tobin Bell , Benjamin Penchas

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from…

Computation and Language · Computer Science 2021-02-03 Nuo Chen , Fenglin Liu , Chenyu You , Peilin Zhou , Yuexian Zou

Although deep pre-trained language models have shown promising benefit in a large set of industrial scenarios, including Click-Through-Rate (CTR) prediction, how to integrate pre-trained language models that handle only textual signals into…

Computation and Language · Computer Science 2023-08-23 Dong Wang , Kavé Salamatian , Yunqing Xia , Weiwei Deng , Qi Zhiang

Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Zihang Dai , Hanxiao Liu , Quoc V. Le , Mingxing Tan

Transformers usually expose one inference cost per trained model, while deployed systems often need multiple cost-quality operating points. We study Budgeted Attention Allocation, a monotone head-gating mechanism conditioned on a requested…

Machine Learning · Computer Science 2026-05-08 Amrit Nidhi

Multivariate time series (MTS) analysis prevails in real-world applications such as finance, climate science and healthcare. The various self-attention mechanisms, the backbone of the state-of-the-art Transformer-based models, efficiently…

Machine Learning · Computer Science 2023-11-21 Quang Minh Nguyen , Lam M. Nguyen , Subhro Das

Motivated by the emerging demand in the financial industry for the automatic analysis of unstructured and structured data at scale, Question Answering (QA) systems can provide lucrative and competitive advantages to companies by…

Computation and Language · Computer Science 2025-05-05 Bithiah Yuan

Transformers have been successful in many vision tasks, thanks to their capability of capturing long-range dependency. However, their quadratic computational complexity poses a major obstacle for applying them to vision tasks requiring…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Shitao Tang , Jiahui Zhang , Siyu Zhu , Ping Tan

Transformer based architectures have become de-facto models used for a range of Natural Language Processing tasks. In particular, the BERT based models achieved significant accuracy gain for GLUE tasks, CoNLL-03 and SQuAD. However, BERT…

Computation and Language · Computer Science 2021-04-21 Sheng Shen , Zhen Dong , Jiayu Ye , Linjian Ma , Zhewei Yao , Amir Gholami , Michael W. Mahoney , Kurt Keutzer

The quadratic cost of attention in transformers motivated the development of efficient approaches: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in…

Machine Learning · Computer Science 2025-11-10 Jatin Prakash , Aahlad Puli , Rajesh Ranganath

We present a systematic investigation of layer-wise BERT activations for general-purpose text representations to understand what linguistic information they capture and how transferable they are across different tasks. Sentence-level…

Computation and Language · Computer Science 2019-10-25 Xiaofei Ma , Zhiguo Wang , Patrick Ng , Ramesh Nallapati , Bing Xiang

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from…

Machine Learning · Computer Science 2025-11-25 Jeffrey Willette , Heejun Lee , Sung Ju Hwang

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.…

Computation and Language · Computer Science 2023-08-03 Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Lukasz Kaiser , Illia Polosukhin

The Transformer architecture deeply changed the natural language processing, outperforming all previous state-of-the-art models. However, well-known Transformer models like BERT, RoBERTa, and GPT-2 require a huge compute budget to create a…

Computation and Language · Computer Science 2021-04-21 Luca Di Liello , Matteo Gabburo , Alessandro Moschitti

Speculation is a naturally occurring phenomena in textual data, forming an integral component of many systems, especially in the biomedical information retrieval domain. Previous work addressing cue detection and scope resolution (the two…

Computation and Language · Computer Science 2020-01-10 Benita Kathleen Britto , Aditya Khandelwal

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

Attention mechanisms, particularly softmax attention, have been instrumental in the success of transformer-based models such as GPT. However, the quadratic memory complexity of softmax attention with respect to sequence length poses…

Machine Learning · Computer Science 2026-02-20 Gabriel Mongaras , Trevor Dohm , Eric C. Larson
‹ Prev 1 3 4 5 6 7 10 Next ›