English
Related papers

Related papers: On Initializing Transformers with Pre-trained Embe…

200 papers

Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and generalization in adversarially trained models involves a…

Computation and Language · Computer Science 2023-12-12 Enes Altinisik , Hassan Sajjad , Husrev Taha Sencar , Safa Messaoud , Sanjay Chawla

Transformers-based pretrained language models achieve outstanding results in many well-known NLU benchmarks. However, while pretraining methods are very convenient, they are expensive in terms of time and resources. This calls for a study…

Computation and Language · Computer Science 2021-09-10 Laura Pérez-Mayos , Miguel Ballesteros , Leo Wanner

Pretrained multilingual text encoders based on neural Transformer architectures, such as multilingual BERT (mBERT) and XLM, have achieved strong performance on a myriad of language understanding tasks. Consequently, they have been adopted…

Computation and Language · Computer Science 2021-01-22 Robert Litschko , Ivan Vulić , Simone Paolo Ponzetto , Goran Glavaš

Pretraining large language models (LLMs) with next-token prediction has led to remarkable advances, yet the context-dependent nature of token embeddings in such models results in high intra-class variance and inter-class similarity, thus…

Computation and Language · Computer Science 2026-05-12 Yan Sun , Guoxia Wang , Jinle Zeng , JiaBin Yang , Shuai Li , Li Shen , Dacheng Tao , DianHai Yu , Haifeng Wang

We introduce a simple yet effective method of integrating contextual embeddings with commonsense graph embeddings, dubbed BERT Infused Graphs: Matching Over Other embeDdings. First, we introduce a preprocessing method to improve the speed…

Computation and Language · Computer Science 2019-10-18 Jeff Da

Recently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research has explored the…

Computation and Language · Computer Science 2020-12-07 Daniel Grießhaber , Johannes Maucher , Ngoc Thang Vu

With the rapid proliferation of textual data, predicting long texts has emerged as a significant challenge in the domain of natural language processing. Traditional text prediction methods encounter substantial difficulties when grappling…

Computation and Language · Computer Science 2024-01-24 Jiahui Zhao , Ziyi Meng , Stepan Gordeev , Zijie Pan , Dongjin Song , Sandro Steinbach , Caiwen Ding

Weight initialization governs signal propagation and gradient flow at the start of training. This paper offers a theory-grounded and empirically validated study across two regimes: compact ReLU multilayer perceptrons and GPT-2-style…

Machine Learning · Computer Science 2025-10-13 Yankun Han

The training of Transformer models has revolutionized natural language processing and computer vision, but it remains a resource-intensive and time-consuming process. This paper investigates the applicability of the early-bird ticket…

Computation and Language · Computer Science 2024-05-07 Shravan Cheekati

Pre-training models are an important tool in Natural Language Processing (NLP), while the BERT model is a classic pre-training model whose structure has been widely adopted by followers. It was even chosen as the reference model for the…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-18 Jinle Zeng , Min Li , Zhihua Wu , Jiaqi Liu , Yuang Liu , Dianhai Yu , Yanjun Ma

Language models (LMs) are increasingly extended with new learnable vocabulary tokens for domain-specific tasks, such as Semantic-ID tokens in generative recommendation. The standard practice initializes these new tokens as the mean of…

Pre-trained language models perform well on a variety of linguistic tasks that require symbolic reasoning, raising the question of whether such models implicitly represent abstract symbols and rules. We investigate this question using the…

Computation and Language · Computer Science 2021-09-16 Jason Wei , Dan Garrette , Tal Linzen , Ellie Pavlick

Recently developed large pre-trained language models, e.g., BERT, have achieved remarkable performance in many downstream natural language processing applications. These pre-trained language models often contain hundreds of millions of…

Computation and Language · Computer Science 2021-06-17 Xinyi Wang , Haiqin Yang , Liang Zhao , Yang Mo , Jianping Shen

Contextualized embeddings such as BERT can serve as strong input representations to NLP tasks, outperforming their static embeddings counterparts such as skip-gram, CBOW and GloVe. However, such embeddings are dynamic, calculated according…

Computation and Language · Computer Science 2020-04-07 Yile Wang , Leyang Cui , Yue Zhang

Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this…

Computation and Language · Computer Science 2024-09-27 Belen Alastruey , Gerard I. Gállego , Marta R. Costa-jussà

One of the most remarkable properties of word embeddings is the fact that they capture certain types of semantic and syntactic relationships. Recently, pre-trained language models such as BERT have achieved groundbreaking results across a…

Computation and Language · Computer Science 2019-12-02 Zied Bouraoui , Jose Camacho-Collados , Steven Schockaert

Transformers are the current state-of-the-art of natural language processing in many domains and are using traction within software engineering research as well. Such models are pre-trained on large amounts of data, usually from the general…

Software Engineering · Computer Science 2022-05-16 Julian von der Mosel , Alexander Trautsch , Steffen Herbold

Recent advances, such as GPT and BERT, have shown success in incorporating a pre-trained transformer language model and fine-tuning operation to improve downstream NLP systems. However, this framework still has some fundamental problems in…

Computation and Language · Computer Science 2019-05-22 Zhongyang Li , Xiao Ding , Ting Liu

In this study, we delve into the efficacy of transformers within pre-trained language models (PLMs) when repurposed as encoders for Automatic Speech Recognition (ASR). Our underlying hypothesis posits that, despite being initially trained…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-27 Keyu An , Shiliang Zhang , Zhijie Yan

In this paper, we compare the performances of traditional machine learning models using feature engineering and word vectors and the state-of-the-art language model BERT using word embeddings on three datasets. We also consider the time and…

Computation and Language · Computer Science 2022-10-31 Ryiaadh Gani , Lisa Chalaguine