English
Related papers

Related papers: CodeArt: Better Code Models by Attention Regulariz…

200 papers

Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to…

Computation and Language · Computer Science 2020-03-25 Kevin Clark , Minh-Thang Luong , Quoc V. Le , Christopher D. Manning

Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically…

Computation and Language · Computer Science 2022-04-20 Ziyang Luo , Yadong Xi , Jing Ma , Zhiwei Yang , Xiaoxi Mao , Changjie Fan , Rongsheng Zhang

Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention…

Computation and Language · Computer Science 2025-04-25 Yaniv Leviathan , Matan Kalman , Yossi Matias

Recurrent neural networks with differentiable attention mechanisms have had success in generative and classification tasks. We show that the classification performance of such models can be enhanced by guiding a randomly initialized model…

Machine Learning · Computer Science 2017-12-18 Jack Lindsey

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Computation and Language · Computer Science 2025-09-23 Alok N. Shah , Khush Gupta , Keshav Ramji , Pratik Chaudhari

Large language models are increasingly solving tasks that are commonly believed to require human-level reasoning ability. However, these models still perform very poorly on benchmarks of general intelligence such as the Abstraction and…

Artificial Intelligence · Computer Science 2024-07-02 Natasha Butt , Blazej Manczak , Auke Wiggers , Corrado Rainone , David W. Zhang , Michaël Defferrard , Taco Cohen

Recently multimodal transformer models have gained popularity because their performance on language and vision tasks suggest they learn rich visual-linguistic representations. Focusing on zero-shot image retrieval tasks, we study three…

Computation and Language · Computer Science 2021-02-02 Lisa Anne Hendricks , John Mellor , Rosalia Schneider , Jean-Baptiste Alayrac , Aida Nematzadeh

Less than 1% of protein sequences are structurally and functionally annotated. Natural Language Processing (NLP) community has recently embraced self-supervised learning as a powerful approach to learn representations from unlabeled text,…

Biomolecules · Quantitative Biology 2020-12-08 Modestas Filipavicius , Matteo Manica , Joris Cadow , Maria Rodriguez Martinez

Learning program representations has been the core prerequisite of code intelligent tasks such as code search and code clone detection. The state-of-the-art pre-trained models such as CodeBERT require the availability of large-scale code…

Software Engineering · Computer Science 2022-04-19 Nan Cui , Yuze Jiang , Xiaodong Gu , Beijun Shen

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Qian-Wei Wang , Yuqiu Xie , Letian Zhang , Zimo Liu , Shu-Tao Xia

Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Yifei Zhang , Siyi Gu , Bo Pan , Guangji Bai , Meikang Qiu , Xiaofeng Yang , Liang Zhao

Recently, pre-trained language models mostly follow the pre-train-then-fine-tuning paradigm and have achieved great performance on various downstream tasks. However, since the pre-training stage is typically task-agnostic and the…

Computation and Language · Computer Science 2020-10-08 Yuxian Gu , Zhengyan Zhang , Xiaozhi Wang , Zhiyuan Liu , Maosong Sun

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Computation and Language · Computer Science 2020-02-11 Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , Radu Soricut

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

Computation and Language · Computer Science 2022-03-25 Le Hou , Richard Yuanzhe Pang , Tianyi Zhou , Yuexin Wu , Xinying Song , Xiaodan Song , Denny Zhou

Much of software-engineering research relies on the naturalness of code, the fact that code, in small code snippets, is repetitive and can be predicted using statistical language models like n-gram. Although powerful, training such models…

Software Engineering · Computer Science 2022-08-15 Ahmed Khanfir , Matthieu Jimenez , Mike Papadakis , Yves Le Traon

In recent years, there has been a wide interest in designing deep neural network-based models that automate downstream software engineering tasks on source code, such as code document generation, code search, and program repair. Although…

Software Engineering · Computer Science 2023-08-30 Ahmad Haji Mohammadkhani , Chakkrit Tantithamthavorn , Hadi Hemmati

Most humans use visual imagination to understand and reason about language, but models such as BERT reason about language using knowledge acquired during text-only pretraining. In this work, we investigate whether vision-and-language…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Morris Alper , Michael Fiman , Hadar Averbuch-Elor

Masked language models like BERT can perform text classification in a zero-shot fashion by reformulating downstream tasks as text infilling. However, this approach is highly sensitive to the template used to prompt the model, yet…

Computation and Language · Computer Science 2022-10-27 Mozes van de Kar , Mengzhou Xia , Danqi Chen , Mikel Artetxe

Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks. However, research in language model pre-training has mostly focused on natural languages, and it is unclear whether…

Computation and Language · Computer Science 2021-10-29 Baptiste Roziere , Marie-Anne Lachaux , Marc Szafraniec , Guillaume Lample

Code Language Models (CodeLLMs) traditionally learn attention based solely on statistical input-output token correlations ("machine attention"). In contrast, human developers rely on intuition, selectively fixating on semantically salient…

Software Engineering · Computer Science 2026-04-21 Yifan Zhang , Chen Huang , Yueke Zhang , Jiahao Zhang , Toby Jia-Jun Li , Collin McMillan , Kevin Leach , Yu Huang