相关论文: Mitigating Catastrophic Forgetting in Multi-domain…

Continual learning-the ability to learn many tasks in sequence-is critical for artificial learning systems. Yet standard training methods for deep networks often suffer from catastrophic forgetting, where learning new tasks erases knowledge…

A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propose a novel framework called ReCL to slow down forgetting in…

Deep learning based question answering (QA) on English documents has achieved success because there is a large amount of English training examples. However, for most languages, training examples for high-quality QA models are not available.…

Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data during its entire lifetime. Although major advances have been made in the field, one recurring problem which remains unsolved is that of…

Class-incremental continual learning addresses catastrophic forgetting by enabling classification models to preserve knowledge of previously learned classes while acquiring new ones. However, the vulnerability of the models against…

Owing to the continuous efforts by the Chinese NLP community, more and more Chinese machine reading comprehension datasets become available. To add diversity in this area, in this paper, we propose a new task called Sentence Cloze-style…

Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem in large-scale supervised classification, little has been done to overcome…

Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as "one" in English and "w\`an" in Chinese. We propose a CTC-based end-to-end…

Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most…

Most dominant neural machine translation (NMT) models are restricted to make predictions only according to the local context of preceding words in a left-to-right manner. Although many previous studies try to incorporate global information…

Knowledge Tracing (KT) aims to trace changes in students' knowledge states throughout their entire learning process by analyzing their historical learning data and predicting their future learning performance. Existing forgetting curve…

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…

Connectionist Temporal Classification (CTC) models are popular for their balance between speed and performance for Automatic Speech Recognition (ASR). However, these CTC models still struggle in other areas, such as personalization towards…

Catastrophic forgetting (CF) happens whenever a neural network overwrites past knowledge while being trained on new tasks. Common techniques to handle CF include regularization of the weights (using, e.g., their importance on past tasks),…

Chinese Grammatical Error Correction (CGEC) aims to generate a correct sentence from an erroneous sequence, where different kinds of errors are mixed. This paper divides the CGEC task into two steps, namely spelling error correction and…

Recently, Chinese word segmentation (CWS) methods using neural networks have made impressive progress. Most of them regard the CWS as a sequence labeling problem which construct models based on local features rather than considering global…

Text correction, especially the semantic correction of more widely used scenes, is strongly required to improve, for the fluency and writing efficiency of the text. An adversarial multi-task learning method is proposed to enhance the…

Chinese spelling check (CSC) is a fundamental NLP task that detects and corrects spelling errors in Chinese texts. As most of these spelling errors are caused by phonetic similarity, effectively modeling the pronunciation of Chinese…

Given the ability to model more realistic and dynamic problems, Federated Continual Learning (FCL) has been increasingly investigated recently. A well-known problem encountered in this setting is the so-called catastrophic forgetting, for…

A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle. However, continually training a model often leads to a well-known…