Related papers: Task-adaptive Pre-training and Self-training are C…

Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the…

One of the most impressive results of recent NLP history is the ability of pre-trained language models to solve new tasks in a zero-shot setting. To achieve this, NLP tasks are framed as natural language prompts, generating a response…

In recent years, language models (LMs) have made remarkable progress in advancing the field of natural language processing (NLP). However, the impact of data augmentation (DA) techniques on the fine-tuning (FT) performance of these LMs has…

While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There…

Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the…

Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art results on various NLP tasks. However, the data discrepancy issue…

Neural Transfer Learning (TL) is becoming ubiquitous in Natural Language Processing (NLP), thanks to its high performance on many tasks, especially in low-resourced scenarios. Notably, TL is widely used for neural domain adaptation to…

Transformer-based pretrained language models (T-PTLMs) have achieved great success in almost every NLP task. The evolution of these models started with GPT and BERT. These models are built on the top of transformers, self-supervised…

Recently, unsupervised pre-training is gaining increasing popularity in the realm of computational linguistics, thanks to its surprising success in advancing natural language understanding (NLU) and the potential to effectively exploit…

Transfer learning (TL) in natural language processing (NLP) has seen a surge of interest in recent years, as pre-trained models have shown an impressive ability to transfer to novel tasks. Three main strategies have emerged for making use…

Language models built from various sources are the foundation of today's NLP progress. However, for many low-resource languages, the diversity of domains is often limited, more biased to a religious domain, which impacts their performance…

Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding tasks. By supplementing language model-style pretraining with further training on…

Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising results by learning to initialize a classification model…

The increasing privacy concerns on personal private text data promote the development of federated learning (FL) in recent years. However, the existing studies on applying FL in NLP are not suitable to coordinate participants with…

We present a simple yet effective Targeted Adversarial Training (TAT) algorithm to improve adversarial training for natural language understanding. The key idea is to introspect current mistakes and prioritize adversarial training steps to…

Test-Time Scaling (TTS) improves the reasoning performance of Large Language Models (LLMs) by allocating additional compute during inference. We conduct a structured survey of TTS methods and categorize them into sampling-based,…

This paper presents a production Semi-Supervised Learning (SSL) pipeline based on the student-teacher framework, which leverages millions of unlabeled examples to improve Natural Language Understanding (NLU) tasks. We investigate two…

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture…

Most previous neural text-to-speech (TTS) methods are mainly based on supervised learning methods, which means they depend on a large training dataset and hard to achieve comparable performance under low-resource conditions. To address this…

Self-training is one of the earliest and simplest semi-supervised methods. The key idea is to augment the original labeled dataset with unlabeled data paired with the model's prediction (i.e. the pseudo-parallel data). While self-training…