Encoder-decoder models can benefit from pre-trained masked language models in grammatical error correction

M Kaneko, M Mita, S Kiyono, J Suzuki, K Inui - arXiv preprint arXiv …, 2020 - arxiv.org
This paper investigates how to effectively incorporate a pre-trained masked language model
(MLM), such as BERT, into an encoder-decoder (EncDec) model for grammatical error …

Bert, mbert, or bibert? a study on contextualized embeddings for neural machine translation

H Xu, B Van Durme, K Murray - arXiv preprint arXiv:2109.04588, 2021 - arxiv.org
The success of bidirectional encoders using masked language models, such as BERT, on
numerous natural language processing tasks has prompted researchers to attempt to …

[Retracted] Explainable AI in Diagnosing and Anticipating Leukemia Using Transfer Learning Method

WH Abir, MF Uddin, FR Khanam, T Tazin… - Computational …, 2022 - Wiley Online Library
White blood cells (WBCs) are blood cells that fight infections and diseases as a part of the
immune system. They are also known as “defender cells.” But the imbalance in the number …

Vesper: A compact and effective pretrained model for speech emotion recognition

W Chen, X Xing, P Chen, X Xu - IEEE Transactions on Affective …, 2024 - ieeexplore.ieee.org
This paper presents a paradigm that adapts general large-scale pretrained models (PTMs)
to speech emotion recognition task. Although PTMs shed new light on artificial general …

Understanding and improving sequence-to-sequence pretraining for neural machine translation

W Wang, W Jiao, Y Hao, X Wang, S Shi, Z Tu… - arXiv preprint arXiv …, 2022 - arxiv.org
In this paper, we present a substantial step in better understanding the SOTA sequence-to-
sequence (Seq2Seq) pretraining for neural machine translation~(NMT). We focus on …

自然语言处理预训练技术综述.

陈德光, 马金林, 马自萍, 周洁 - Journal of Frontiers of …, 2021 - search.ebscohost.com
在目前已发表的自然语言处理预训练技术综述中, 大多数文章仅介绍神经网络预训练技术或者极
简单介绍传统预训练技术, 存在人为割裂自然语言预训练发展历程. 为此, 以自然语言预训练发展 …

Incorporating bert into parallel sequence decoding with adapters

J Guo, Z Zhang, L Xu, HR Wei… - Advances in Neural …, 2020 - proceedings.neurips.cc
While large scale pre-trained language models such as BERT have achieved great success
on various natural language understanding tasks, how to efficiently and effectively …

Training-free lexical backdoor attacks on language models

Y Huang, TY Zhuo, Q Xu, H Hu, X Yuan… - Proceedings of the ACM …, 2023 - dl.acm.org
Large-scale language models have achieved tremendous success across various natural
language processing (NLP) applications. Nevertheless, language models are vulnerable to …

MSP: Multi-stage prompting for making pre-trained language models better translators

Z Tan, X Zhang, S Wang, Y Liu - arXiv preprint arXiv:2110.06609, 2021 - arxiv.org
Prompting has recently been shown as a promising approach for applying pre-trained
language models to perform downstream tasks. We present Multi-Stage Prompting (MSP), a …

Understanding multi-turn toxic behaviors in open-domain chatbots

B Chen, G Wang, H Guo, Y Wang, Q Yan - Proceedings of the 26th …, 2023 - dl.acm.org
Recent advances in natural language processing and machine learning have led to the
development of chatbot models, such as ChatGPT, that can engage in conversational …