相关论文: Task Relation Distillation and Prototypical Pseudo…

New Intent Discovery (NID) strives to identify known and reasonably deduce novel intent groups in the open-world scenario. But current methods face issues with inaccurate pseudo-labels and poor representation learning, creating a negative…

Deep learning models have achieved state-of-the-art performance in many computer vision tasks. However, in real-world scenarios, novel classes that were unseen during training often emerge, requiring models to acquire new knowledge…

There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…

Lately, instruction-based techniques have made significant strides in improving performance in few-shot learning scenarios. They achieve this by bridging the gap between pre-trained language models and fine-tuning for specific downstream…

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a…

Distantly-supervised relation extraction (RE) is an effective method to scale RE to large corpora but suffers from noisy labels. Existing approaches try to alleviate noise through multi-instance learning and by providing additional…

Deep learning models rely heavily on large volumes of labeled data to achieve high performance. However, real-world datasets often contain noisy labels due to human error, ambiguity, or resource constraints during the annotation process.…

Offline Reinforcement Learning (RL) aims to learn effective policies from a static dataset without requiring further agent-environment interactions. However, its practical adoption is often hindered by the need for explicit reward…

Deep and large pre-trained language models are the state-of-the-art for various natural language processing tasks. However, the huge size of these models could be a deterrent to use them in practice. Some recent and concurrent works use…

Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen…

Multi-Task Learning (MTL) is widely-accepted in Natural Language Processing as a standard technique for learning multiple related tasks in one model. Training an MTL model requires having the training data for all tasks available at the…

Recent advances in named entity recognition (NER) have pushed the boundary of the task to incorporate visual signals, leading to many variants, including multi-modal NER (MNER) or grounded MNER (GMNER). A key challenge to these tasks is…

Catastrophic forgetting, the tendency of neural networks to forget previously learned knowledge when learning new tasks, has been a major challenge in continual learning (CL). To tackle this challenge, CL methods have been proposed and…

Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect…

Named entity recognition on the in-domain supervised and few-shot settings have been extensively discussed in the NLP community and made significant progress. However, cross-domain NER, a more common task in practical scenarios, still poses…

Named entity recognition (NER) is usually developed and tested on text from well-written sources. However, in intelligent voice assistants, where NER is an important component, input to NER may be noisy because of user or speech recognition…

Decision transformer based sequential policies have emerged as a powerful paradigm in offline reinforcement learning (RL), yet their efficacy remains constrained by the quality of static datasets and inherent architectural limitations.…

Domain incremental learning (DIL) poses a significant challenge in real-world scenarios, as models need to be sequentially trained on diverse domains over time, all the while avoiding catastrophic forgetting. Mitigating representation…

Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samples of new categories arrive incrementally, which requires…

Session-based recommendation has received growing attention recently due to the increasing privacy concern. Despite the recent success of neural session-based recommenders, they are typically developed in an offline manner using a static…