English
Related papers

Related papers: AutoBERT-Zero: Evolving BERT Backbone from Scratch

200 papers

In this paper, we introduce the range of oBERTa language models, an easy-to-use set of language models which allows Natural Language Processing (NLP) practitioners to obtain between 3.8 and 24.3 times faster models without expertise in…

Computation and Language · Computer Science 2023-06-07 Daniel Campos , Alexandre Marques , Mark Kurtz , ChengXiang Zhai

The automation of neural architecture design has been a coveted alternative to human experts. Recent works have small search space, which is easier to optimize but has a limited upper bound of the optimal solution. Extra human design is…

Computer Vision and Pattern Recognition · Computer Science 2021-08-19 Yuanzheng Ci , Chen Lin , Ming Sun , Boyu Chen , Hongwen Zhang , Wanli Ouyang

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to…

Computer Vision and Pattern Recognition · Computer Science 2020-01-01 Yukang Chen , Tong Yang , Xiangyu Zhang , Gaofeng Meng , Xinyu Xiao , Jian Sun

We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones are found to achieve impressive performance for image…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Boyu Chen , Peixia Li , Chuming Li , Baopu Li , Lei Bai , Chen Lin , Ming Sun , Junjie yan , Wanli Ouyang

This paper introduces a cutting-edge approach to cross-modal interaction for tiny object detection by combining semantic-guided natural language processing with advanced visual recognition backbones. The proposed method integrates the BERT…

Computer Vision and Pattern Recognition · Computer Science 2025-11-10 Xian-Hong Huang , Hui-Kai Su , Chi-Chia Sun , Jun-Wei Hsieh

Transformers that are pre-trained on multilingual corpora, such as, mBERT and XLM-RoBERTa, have achieved impressive cross-lingual transfer capabilities. In the zero-shot transfer setting, only English training data is used, and the…

Computation and Language · Computer Science 2021-09-13 Yang Chen , Alan Ritter

Evolutionary computation (EC)-based neural architecture search (NAS) has achieved remarkable performance in the automatic design of neural architectures. However, the high computational cost associated with evaluating searched architectures…

Neural and Evolutionary Computing · Computer Science 2025-05-01 Yangyang Li , Guanlong Liu , Ronghua Shang , Licheng Jiao

We present BERTGEN, a novel generative, decoder-only model which extends BERT by fusing multimodal and multilingual pretrained models VL-BERT and M-BERT, respectively. BERTGEN is auto-regressively trained for language generation tasks,…

Computation and Language · Computer Science 2021-06-08 Faidon Mitzalis , Ozan Caglayan , Pranava Madhyastha , Lucia Specia

Hardware-Aware Neural Architecture Search (HW-NAS) requires joint optimization of accuracy and latency under device constraints. Traditional supernet-based methods require multiple GPU days per dataset. Large Language Model (LLM)-driven…

Machine Learning · Computer Science 2025-12-08 Hengyi Zhu , Grace Li Zhang , Shaoyi Huang

This paper presents a framework for Named Entity Recognition (NER) leveraging the Bidirectional Encoder Representations from Transformers (BERT) model in natural language processing (NLP). NER is a fundamental task in NLP with broad…

Computation and Language · Computer Science 2025-05-06 Mo Sun , Siheng Xiong , Yuankai Cai , Bowen Zuo

The standard BERT adopts subword-based tokenization, which may break a word into two or more wordpieces (e.g., converting "lossless" to "loss" and "less"). This will bring inconvenience in following situations: (1) what is the best way to…

Computation and Language · Computer Science 2022-02-25 Zhangyin Feng , Duyu Tang , Cong Zhou , Junwei Liao , Shuangzhi Wu , Xiaocheng Feng , Bing Qin , Yunbo Cao , Shuming Shi

The surge of pre-trained language models has begun a new era in the field of Natural Language Processing (NLP) by allowing us to build powerful language models. Among these models, Transformer-based models such as BERT have become…

Computation and Language · Computer Science 2021-10-12 Mehrdad Farahani , Mohammad Gharachorloo , Marzieh Farahani , Mohammad Manthouri

Contextualized word embeddings derived from pre-trained language models (LMs) show significant improvements on downstream NLP tasks. Pre-training on domain-specific corpora, such as biomedical articles, further improves their performance.…

Computation and Language · Computer Science 2019-04-05 Qiao Jin , Bhuwan Dhingra , William W. Cohen , Xinghua Lu

Pretrained language models have served as important backbones for natural language processing. Recently, in-domain pretraining has been shown to benefit various domain-specific downstream tasks. In the biomedical domain, natural language…

Computation and Language · Computer Science 2022-04-25 Hongyi Yuan , Zheng Yuan , Ruyi Gan , Jiaxing Zhang , Yutao Xie , Sheng Yu

Intent classification and slot filling are two essential tasks for natural language understanding. They often suffer from small-scale human-labeled training data, resulting in poor generalization capability, especially for rare words.…

Computation and Language · Computer Science 2019-03-01 Qian Chen , Zhu Zhuo , Wen Wang

Multimodal learning pipelines have benefited from the success of pretrained language models. However, this comes at the cost of increased model parameters. In this work, we propose Adapted Multimodal BERT (AMB), a BERT-based architecture…

Computation and Language · Computer Science 2022-12-02 Odysseas S. Chlapanis , Georgios Paraskevopoulos , Alexandros Potamianos

The BERT model has arisen as a popular state-of-the-art machine learning model in the recent years that is able to cope with multiple NLP tasks such as supervised text classification without human supervision. Its flexibility to cope with…

Computation and Language · Computer Science 2023-04-26 Santiago González-Carvajal , Eduardo C. Garrido-Merchán

This paper investigates the problem of learning cross-lingual representations in a contextual space. We propose Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextualized word…

Computation and Language · Computer Science 2019-09-17 Yuxuan Wang , Wanxiang Che , Jiang Guo , Yijia Liu , Ting Liu

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

Computation and Language · Computer Science 2022-01-19 Dongkuan Xu , Ian E. H. Yen , Jinxi Zhao , Zhibin Xiao

Pre-trained language models, such as BERT, have achieved significant accuracy gain in many natural language processing tasks. Despite its effectiveness, the huge number of parameters makes training a BERT model computationally very…

Computation and Language · Computer Science 2020-11-30 Cheng Yang , Shengnan Wang , Chao Yang , Yuechuan Li , Ru He , Jingqiao Zhang
‹ Prev 1 8 9 10 Next ›