Related papers: Prototypical Contrastive Transfer Learning for Mul…

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level features for the…

Capturing emotions within a conversation plays an essential role in modern dialogue systems. However, the weak correlation between emotions and semantics brings many challenges to emotion recognition in conversation (ERC). Even semantically…

New intent discovery is a crucial capability for task-oriented dialogue systems. Existing methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data through pre-training and clustering stages. They either…

Contrastive self-supervised learning (CSL) with a prototypical regularization has been introduced in learning meaningful representations for downstream tasks that require strong semantic information. However, to optimize CSL with a loss…

The vision-language navigation (VLN) task requires an agent to reach a target with the guidance of natural language instruction. Previous works learn to navigate step-by-step following an instruction. However, these works may fail to…

Deep models have been widely and successfully used in image manipulation detection, which aims to classify tampered images and localize tampered regions. Most existing methods mainly focus on extracting global features from tampered images,…

Many pretrained multilingual models exhibit cross-lingual transfer ability, which is often attributed to a learned language-neutral representation during pretraining. However, it remains unclear what factors contribute to the learning of a…

The ability to evolve is fundamental for any valuable autonomous agent whose knowledge cannot remain limited to that injected by the manufacturer. Consider for example a home assistant robot: it should be able to incrementally learn new…

This paper considers contrastive training for cross-modal 0-shot transfer wherein a pre-trained model in one modality is used for representation learning in another domain using pairwise data. The learnt models in the latter domain can then…

Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features…

Packet loss concealment (PLC) is challenging in concealing missing contents both plausibly and naturally when there are only limited available context to use. Recently deep-learning based PLC algorithms have demonstrated their superiority…

Multilingual pretraining has been a successful solution to the challenges posed by the lack of resources for languages. These models can transfer knowledge to target languages with minimal or no examples. Recent research suggests that…

Traditional approaches to RL have focused on learning decision policies directly from episodic decisions, while slowly and implicitly learning the semantics of compositional representations needed for generalization. While some approaches…

Contrastive Language Image Pretraining (CLIP) has received widespread attention, since its learned representations can be transferred well to various downstream tasks. During the training process of the CLIP model, the InfoNCE objective…

Modern NLP applications have enjoyed a great boost utilizing neural networks models. Such deep neural models, however, are not applicable to most human languages due to the lack of annotated training data for various NLP tasks.…

Currently, pre-trained language models (PLMs) do not cope well with the distribution shift problem, resulting in models trained on the training set failing in real test scenarios. To address this problem, the test-time adaptation (TTA)…

This paper addresses the limitations of large-scale language models in safety alignment and robustness by proposing a fine-tuning method that combines contrastive distillation with noise-robust training. The method freezes the backbone…

Existed pre-trained models have achieved state-of-the-art performance on various text classification tasks. These models have proven to be useful in learning universal language representations. However, the semantic discrepancy between…

Transfer learning enhances learning across tasks, by leveraging previously learned representations -- if they are properly chosen. We describe an efficient method to accurately estimate the appropriateness of a previously trained model for…

Recent studies have demonstrated the overwhelming advantage of cross-lingual pre-trained models (PTMs), such as multilingual BERT and XLM, on cross-lingual NLP tasks. However, existing approaches essentially capture the co-occurrence among…