Continual adaptation for efficient machine communication
To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent neural language models are able to comprehend and produce the existing conventions present in their training data, but are not able to flexibly and interactively adapt those conventions on the fly as humans do. We introduce an interactive repeated reference task as a benchmark for models of adaptation in communication and propose a regularized continual learning framework that allows an artificial agent initialized with a generic language model to more accurately and efficiently communicate with a partner over time. We evaluate this framework through simulations on COCO and in real-time reference game experiments with human partners.
Code (1)
Tasks
Continual LearningLanguage ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Continual adaptation for efficient machine communication
To communicate with new partners in new contexts, humans rapidly form new linguistic conventions. Recent language models trained with deep neural networks are able to comprehend and produce the existing conventions prese…
Continual LearningLanguage ModelingLanguage ModellingContinual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation
Continual Machine Reading Comprehension aims to incrementally learn from a continuous data stream across time without access the previous seen data, which is crucial for the development of real-world MRC systems. However…
Domain AdaptationIncremental LearningMachine Reading ComprehensionReading ComprehensionSPD-CFL: Stepwise Parameter Dropout for Efficient Continual Federated Learning
Federated Learning (FL) is a collaborative machine learning paradigm for training models on local sensitive data with privacy protection. Pre-trained transformer-based models have emerged as useful foundation models (FMs…
Continual LearningFederated Learningparameter-efficient fine-tuningTransfer LearningViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existin…
Test-time AdaptationContinual Domain Adaptation for Machine Reading Comprehension
Machine reading comprehension (MRC) has become a core component in a variety of natural language processing (NLP) applications such as question answering and dialogue systems. It becomes a practical challenge that an MRC…
Continual LearningDomain AdaptationMachine Reading ComprehensionQuestion Answering+1