English
Related papers

Related papers: Progressively Stacking 2.0: A Multi-stage Layerwis…

200 papers

Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as…

Computation and Language · Computer Science 2019-09-30 Wei Wang , Bin Bi , Ming Yan , Chen Wu , Zuyi Bao , Jiangnan Xia , Liwei Peng , Luo Si

In recent years, large language models (LLMs) have demonstrated significant potential in complex reasoning tasks like mathematical problem-solving. However, existing research predominantly relies on reinforcement learning (RL) frameworks…

Machine Learning · Computer Science 2026-01-12 ShaoZhen Liu , Xinting Huang , Houwen Peng , Xin Chen , Xinyang Song , Qi Li , Zhenan Sun

BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its…

Computation and Language · Computer Science 2019-10-25 Raghavendra Pappagari , Piotr Żelasko , Jesús Villalba , Yishay Carmiel , Najim Dehak

Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the…

Computation and Language · Computer Science 2020-04-21 Anne Lauscher , Ivan Vulić , Edoardo Maria Ponti , Anna Korhonen , Goran Glavaš

A Lite BERT (ALBERT) has been introduced to scale up deep bidirectional representation learning for natural languages. Due to the lack of pretrained ALBERT models for Korean language, the best available practice is the multilingual model or…

Computation and Language · Computer Science 2021-01-28 Hyunjae Lee , Jaewoong Yoon , Bonggyu Hwang , Seongho Joe , Seungjai Min , Youngjune Gwon

Recently, prompt tuning (PT) has gained increasing attention as a parameter-efficient way of tuning pre-trained language models (PLMs). Despite extensively reducing the number of tunable parameters and achieving satisfying performance, PT…

Computation and Language · Computer Science 2022-11-15 Yufei Huang , Yujia Qin , Huadong Wang , Yichun Yin , Maosong Sun , Zhiyuan Liu , Qun Liu

Large-scale pre-trained language models have shown remarkable results in diverse NLP applications. Unfortunately, these performance gains have been accompanied by a significant increase in computation time and model size, stressing the need…

Computation and Language · Computer Science 2021-09-27 Cristóbal Eyzaguirre , Felipe del Río , Vladimir Araujo , Álvaro Soto

Modern recommendation systems rely on real-valued embeddings of categorical features. Increasing the dimension of embedding vectors improves model accuracy but comes at a high cost to model size. We introduce a multi-layer embedding…

Machine Learning · Computer Science 2020-06-11 Benjamin Ghaemmaghami , Zihao Deng , Benjamin Cho , Leo Orshansky , Ashish Kumar Singh , Mattan Erez , Michael Orshansky

Fine-tuning pre-trained language models such as BERT has become a common practice dominating leaderboards across various NLP tasks. Despite its recent success and wide adoption, this process is unstable when there are only a small number of…

Computation and Language · Computer Science 2021-07-13 Hang Hua , Xingjian Li , Dejing Dou , Cheng-Zhong Xu , Jiebo Luo

Transformer-based pre-trained language models, such as BERT, achieve great success in various natural language understanding tasks. Prior research found that BERT captures a rich hierarchy of linguistic information at different layers.…

Computation and Language · Computer Science 2023-07-17 Qian Chen , Wen Wang , Qinglin Zhang , Chong Deng , Ma Yukun , Siqi Zheng

In this paper, we propose a novel pretraining-based encoder-decoder framework, which can generate the output sequence based on the input sequence in a two-stage manner. For the encoder of our model, we encode the input sequence into context…

Computation and Language · Computer Science 2019-10-16 Haoyu Zhang , Jianjun Xu , Ji Wang

It has been shown that multilingual BERT (mBERT) yields high quality multilingual representations and enables effective zero-shot transfer. This is surprising given that mBERT does not use any crosslingual signal during training. While…

Computation and Language · Computer Science 2021-02-09 Philipp Dufter , Hinrich Schütze

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

Training large deep neural networks on massive datasets is computationally very challenging. There has been recent surge in interest in using large batch stochastic optimization methods to tackle this issue. The most prominent algorithm in…

The transformer-based pre-trained language model BERT has helped to improve state-of-the-art performance on many natural language processing (NLP) tasks. Using the same architecture and parameters, we developed and evaluated a monolingual…

Computation and Language · Computer Science 2019-12-23 Wietse de Vries , Andreas van Cranenburgh , Arianna Bisazza , Tommaso Caselli , Gertjan van Noord , Malvina Nissim

Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages. We study the word-level translation information embedded in mBERT and present two simple…

Computation and Language · Computer Science 2020-10-19 Hila Gonen , Shauli Ravfogel , Yanai Elazar , Yoav Goldberg

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However,…

Computation and Language · Computer Science 2023-03-07 Zhen Wang , Rameswar Panda , Leonid Karlinsky , Rogerio Feris , Huan Sun , Yoon Kim

Pre-trained language models in the past years have shown exponential growth in model parameters and compute time. ELECTRA is a novel approach for improving the compute efficiency of pre-trained language models (e.g. BERT) based on masked…

Computation and Language · Computer Science 2021-10-14 Junmo Kang , Suwon Shin , Jeonghwan Kim , Jaeyoung Jo , Sung-Hyon Myaeng

Pre-trained Language Models (PLMs), like BERT, with self-supervision objectives exhibit remarkable performance and generalization across various tasks. However, they suffer in inference latency due to their large size. To address this…

Computation and Language · Computer Science 2024-05-27 Divya Jyoti Bajpai , Manjesh Kumar Hanawal

Transformer-based pre-training models like BERT have achieved remarkable performance in many natural language processing tasks.However, these models are both computation and memory expensive, hindering their deployment to…

Computation and Language · Computer Science 2020-10-13 Wei Zhang , Lu Hou , Yichun Yin , Lifeng Shang , Xiao Chen , Xin Jiang , Qun Liu