English
Related papers

Related papers: To BERT or Not to BERT: Comparing Task-specific an…

200 papers

While machine learning approaches to visual recognition offer great promise, most of the existing methods rely heavily on the availability of large quantities of labeled training data. However, in the vast majority of real-world settings,…

Computer Vision and Pattern Recognition · Computer Science 2020-08-14 Akash Gupta , Rameswar Panda , Sujoy Paul , Jianming Zhang , Amit K. Roy-Chowdhury

The ability to learn from large unlabeled corpora has allowed neural language models to advance the frontier in natural language understanding. However, existing self-supervision techniques operate at the word form level, which serves as a…

Computation and Language · Computer Science 2020-05-19 Yoav Levine , Barak Lenz , Or Dagan , Ori Ram , Dan Padnos , Or Sharir , Shai Shalev-Shwartz , Amnon Shashua , Yoav Shoham

Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. In this work, we propose a contrastive learning method that utilizes…

Computation and Language · Computer Science 2021-06-15 Taeuk Kim , Kang Min Yoo , Sang-goo Lee

Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and model interpretability. Adversarial training (AT) for attention…

Computation and Language · Computer Science 2022-12-27 Shunsuke Kitada , Hitoshi Iyatomi

In the present paper, two models are presented namely LSTM-CRF and BERT-LSTM-CRF for semantic tagging of universal semantic tag dataset. The experiments show that the first model is much easier to converge while the second model that…

Computation and Language · Computer Science 2023-01-31 Farshad Noravesh

Unsupervised models can provide supplementary soft constraints to help classify new, "target" data since similar instances in the target set are more likely to share the same class label. Such models can also help detect possible…

Machine Learning · Computer Science 2012-06-06 Ayan Acharya , Eduardo R. Hruschka , Joydeep Ghosh , Sreangsu Acharyya

One of the most popular paradigms of applying large pre-trained NLP models such as BERT is to fine-tune it on a smaller dataset. However, one challenge remains as the fine-tuned model often overfits on smaller datasets. A symptom of this…

Computation and Language · Computer Science 2021-10-25 Yiren Chen , Xiaoyu Kou , Jiangang Bai , Yunhai Tong

Pre-trained contextual representations (e.g., BERT) have become the foundation to achieve state-of-the-art results on many NLP tasks. However, large-scale pre-training is computationally expensive. ELECTRA, an early attempt to accelerate…

Computation and Language · Computer Science 2020-06-17 Zhenhui Xu , Linyuan Gong , Guolin Ke , Di He , Shuxin Zheng , Liwei Wang , Jiang Bian , Tie-Yan Liu

Pre-trained word embeddings learned from unlabeled text have become a standard component of neural network architectures for NLP tasks. However, in most cases, the recurrent network that operates on word-level representations to produce…

Computation and Language · Computer Science 2017-05-02 Matthew E. Peters , Waleed Ammar , Chandra Bhagavatula , Russell Power

Topic segmentation of meetings is the task of dividing multi-person meeting transcripts into topic blocks. Supervised approaches to the problem have proven intractable due to the difficulties in collecting and accurately annotating large…

Machine Learning · Computer Science 2021-06-25 Alessandro Solbiati , Kevin Heffernan , Georgios Damaskinos , Shivani Poddar , Shubham Modi , Jacques Cali

Foundation vision-language models have enabled remarkable zero-shot transferability of the pre-trained representations to a wide range of downstream tasks. However, to solve a new task, zero-shot transfer still necessitates human guidance…

Machine Learning · Computer Science 2024-06-12 Artyom Gadetsky , Yulun Jiang , Maria Brbic

In order to train robust deep learning models, large amounts of labelled data is required. However, in the absence of such large repositories of labelled data, unlabeled data can be exploited for the same. Semi-Supervised learning aims to…

Machine Learning · Computer Science 2021-07-20 Soumyadeep Ghosh , Sanjay Kumar , Janu Verma , Awanish Kumar

Deep learning methods have advanced quickly in brain imaging analysis over the past few years, but they are usually restricted by the limited labeled data. Pre-trained model on unlabeled data has presented promising improvement in feature…

Neurons and Cognition · Quantitative Biology 2024-08-22 Jinlong Hu , Yangmin Huang , Nan Wang , Shoubin Dong

Malicious URL detection and webpage classification are critical tasks in cybersecurity and information management. In recent years, extensive research has explored using BERT or similar language models to replace traditional machine…

Cryptography and Security · Computer Science 2025-05-27 Yujie Li , Yiwei Liu , Peiyue Li , Yifan Jia , Yanbin Wang

Transfer learning in natural language processing (NLP), as realized using models like BERT (Bi-directional Encoder Representation from Transformer), has significantly improved language representation with models that can tackle challenging…

Hardware Architecture · Computer Science 2021-04-20 Suchita Pati , Shaizeen Aga , Nuwan Jayasena , Matthew D. Sinclair

We present, to our knowledge, the first application of BERT to document classification. A few characteristics of the task might lead one to think that BERT is not the most appropriate model: syntactic structures matter less for content…

Computation and Language · Computer Science 2019-08-23 Ashutosh Adhikari , Achyudh Ram , Raphael Tang , Jimmy Lin

Few-shot learning-the ability to train models with access to limited data-has become increasingly popular in the natural language processing (NLP) domain, as large language models such as GPT and T0 have been empirically shown to achieve…

Software Engineering · Computer Science 2023-06-16 Robert Kraig Helmeczi , Mucahit Cevik , Savas Yıldırım

Obtaining annotations for 3D medical images is expensive and time-consuming, despite its importance for automating segmentation tasks. Although multi-task learning is considered an effective method for training segmentation models using…

Computer Vision and Pattern Recognition · Computer Science 2020-09-24 Junichiro Iwasawa , Yuichiro Hirano , Yohei Sugawara

Machine learning models are commonly used for malware classification; however, they suffer from performance degradation over time due to concept drift. Adapting these models to changing data distributions requires frequent updates, which…

Machine Learning · Computer Science 2025-08-05 Md Tanvirul Alam , Aritran Piplai , Nidhi Rastogi

Recent work has uncovered the interesting (and somewhat surprising) finding that training models to be invariant to adversarial perturbations requires substantially larger datasets than those required for standard classification. This…

Machine Learning · Computer Science 2019-12-06 Jonathan Uesato , Jean-Baptiste Alayrac , Po-Sen Huang , Robert Stanforth , Alhussein Fawzi , Pushmeet Kohli