English
Related papers

Related papers: A Closer Look at How Fine-tuning Changes BERT

200 papers

As NLP models become larger, executing a trained model requires significant computational resources incurring monetary and environmental costs. To better respect a given inference budget, we propose a modification to contextual…

Computation and Language · Computer Science 2020-05-12 Roy Schwartz , Gabriel Stanovsky , Swabha Swayamdipta , Jesse Dodge , Noah A. Smith

BERT has achieved impressive performance in several NLP tasks. However, there has been limited investigation on its adaptation guidelines in specialised domains. Here we focus on the legal domain, where we explore several approaches for…

Computation and Language · Computer Science 2020-10-07 Ilias Chalkidis , Manos Fergadiotis , Prodromos Malakasiotis , Nikolaos Aletras , Ion Androutsopoulos

Fine-tuning pre-trained language models (PTLMs), such as BERT and its better variant RoBERTa, has been a common practice for advancing performance in natural language understanding (NLU) tasks. Recent advance in representation learning…

Computation and Language · Computer Science 2021-02-05 Wenxuan Zhou , Bill Yuchen Lin , Xiang Ren

The introduction of pre-trained language models has revolutionized natural language research communities. However, researchers still know relatively little regarding their theoretical and empirical properties. In this regard, Peters et al.…

Computation and Language · Computer Science 2019-07-12 Ran Wang , Haibo Su , Chunye Wang , Kailin Ji , Jupeng Ding

Despite the success of fine-tuning pretrained language encoders like BERT for downstream natural language understanding (NLU) tasks, it is still poorly understood how neural networks change after fine-tuning. In this work, we use centered…

Computation and Language · Computer Science 2021-09-21 Jason Phang , Haokun Liu , Samuel R. Bowman

The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks…

Computation and Language · Computer Science 2020-02-18 Jinhua Zhu , Yingce Xia , Lijun Wu , Di He , Tao Qin , Wengang Zhou , Houqiang Li , Tie-Yan Liu

In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set…

Computation and Language · Computer Science 2024-02-27 Alessio Miaschi , Dominique Brunato , Felice Dell'Orletta , Giulia Venturi

Several studies have been carried out on revealing linguistic features captured by BERT. This is usually achieved by training a diagnostic classifier on the representations obtained from different layers of BERT. The subsequent…

Computation and Language · Computer Science 2021-09-14 Hosein Mohebbi , Ali Modarressi , Mohammad Taher Pilehvar

Deploying natural language processing (NLP) models on mobile platforms requires models that can adapt across diverse applications while remaining efficient in memory and computation. We investigate pre-finetuning strategies to enhance the…

Computation and Language · Computer Science 2025-10-10 Junyi Zhu , Savas Ozkan , Andrea Maracani , Sinan Mutlu , Cho Jung Min , Mete Ozay

Currently, the most widespread neural network architecture for training language models is the so called BERT which led to improvements in various Natural Language Processing (NLP) tasks. In general, the larger the number of parameters in a…

Computation and Language · Computer Science 2021-11-02 Jochen Zöllner , Konrad Sperfeld , Christoph Wick , Roger Labahn

We propose pre-finetuning, an additional large-scale learning stage between language model pre-training and fine-tuning. Pre-finetuning is massively multi-task learning (around 50 datasets, over 4.8 million total labeled examples), and is…

Computation and Language · Computer Science 2021-01-28 Armen Aghajanyan , Anchit Gupta , Akshat Shrivastava , Xilun Chen , Luke Zettlemoyer , Sonal Gupta

Pretraining deep language models has led to large performance gains in NLP. Despite this success, Schick and Sch\"utze (2020) recently showed that these models struggle to understand rare words. For static word embeddings, this problem has…

Computation and Language · Computer Science 2020-04-30 Timo Schick , Hinrich Schütze

Fine-tuning pretrained contextual word embedding models to supervised downstream tasks has become commonplace in natural language processing. This process, however, is often brittle: even with the same hyperparameter values, distinct random…

Computation and Language · Computer Science 2020-02-19 Jesse Dodge , Gabriel Ilharco , Roy Schwartz , Ali Farhadi , Hannaneh Hajishirzi , Noah Smith

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

Probing complex language models has recently revealed several insights into linguistic and semantic patterns found in the learned representations. In this paper, we probe BERT specifically to understand and measure the relational knowledge…

Computation and Language · Computer Science 2021-09-09 Jonas Wallat , Jaspreet Singh , Avishek Anand

In recent times, BERT-based models have been extremely successful in solving a variety of natural language processing (NLP) tasks such as reading comprehension, natural language inference, sentiment analysis, etc. All BERT-based…

Computation and Language · Computer Science 2023-04-06 Sharath Nittur Sridhar , Anthony Sarah

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

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

Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…

Computation and Language · Computer Science 2020-10-13 Mengjie Zhao , Philipp Dufter , Yadollah Yaghoobzadeh , Hinrich Schütze

Deep learning approaches are superior in NLP due to their ability to extract informative features and patterns from languages. The two most successful neural architectures are LSTM and transformers, used in large pretrained language models…

Computation and Language · Computer Science 2022-03-03 Matej Klemen , Luka Krsnik , Marko Robnik-Šikonja