Related papers: Towards Fine-tuning Pre-trained Language Models wi…
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…
Pre-trained BERT models have achieved impressive performance in many natural language processing (NLP) tasks. However, in many real-world situations, textual data are usually decentralized over many clients and unable to be uploaded to a…
Transfer learning from pre-trained neural language models towards downstream tasks has been a predominant theme in NLP recently. Several researchers have shown that deep NLP models learn non-trivial amount of linguistic knowledge, captured…
Contextual Embeddings have yielded state-of-the-art results in various natural language processing tasks. However, these embeddings are constrained by models requiring large amounts of data and huge computing power. This is an issue for…
Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised…
Aspect based sentiment analysis aims to identify the sentimental tendency towards a given aspect in text. Fine-tuning of pretrained BERT performs excellent on this task and achieves state-of-the-art performances. Existing BERT-based works…
Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous computation resources and extremely long training time for both…
Prior research notes that BERT's computational cost grows quadratically with sequence length thus leading to longer training times, higher GPU memory constraints and carbon emissions. While recent work seeks to address these scalability…
Language identification is the task of automatically determining the identity of a language conveyed by a spoken segment. It has a profound impact on the multilingual interoperability of an intelligent speech system. Despite language…
This paper addresses the critical challenge of developing computationally efficient hate speech detection systems that maintain competitive performance while being practical for real-time deployment. We propose a novel three-layer framework…
Due to the excessive cost of large-scale language model pre-training, considerable efforts have been made to train BERT progressively -- start from an inferior but low-cost model and gradually grow the model to increase the computational…
Machine reading comprehension is an essential natural language processing task, which takes into a pair of context and query and predicts the corresponding answer to query. In this project, we developed an end-to-end question answering…
Sentiment classification is an important process in understanding people's perception towards a product, service, or topic. Many natural language processing models have been proposed to solve the sentiment classification problem. However,…
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…
While pre-training and fine-tuning, e.g., BERT~\citep{devlin2018bert}, GPT-2~\citep{radford2019language}, have achieved great success in language understanding and generation tasks, the pre-trained models are usually too big for online…
With the yearning for deep learning democratization, there are increasing demands to implement Transformer-based natural language processing (NLP) models on resource-constrained devices for low-latency and high accuracy. Existing BERT…
User reviews have an essential role in the success of the developed mobile apps. User reviews in the textual form are unstructured data, creating a very high complexity when processed for sentiment analysis. Previous approaches that have…
Large-scale pre-trained language models such as BERT are popular solutions for text classification. Due to the superior performance of these advanced methods, nowadays, people often directly train them for a few epochs and deploy the…
Accuracy of English-language Question Answering (QA) systems has improved significantly in recent years with the advent of Transformer-based models (e.g., BERT). These models are pre-trained in a self-supervised fashion with a large English…
Large, pre-trained transformer-based language models such as BERT have drastically changed the Natural Language Processing (NLP) field. We present a survey of recent work that uses these large language models to solve NLP tasks via…